Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 440 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5388. Min Range: -12.5388
Max Act: 12.5388. Min Act: -0.1700
Data Index: 6519431 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5388. Min Range: -12.5388
Max Act: 12.4763. Min Act: -0.1700
Data Index: 3945774 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5388. Min Range: -12.5388
Max Act: 12.1013. Min Act: -0.1700
Data Index: 8288674 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5388. Min Range: -12.5388
Max Act: 12.0388. Min Act: -0.1700
Data Index: 5667901 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5388. Min Range: -12.5388
Max Act: 11.9138. Min Act: -0.1700
Data Index: 260085 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5388. Min Range: -12.5388
Max Act: 11.7888. Min Act: -0.1700
Data Index: 7183130 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5388. Min Range: -12.5388
Max Act: 11.7263. Min Act: -0.1700
Data Index: 974467 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5388. Min Range: -12.5388
Max Act: 11.6638. Min Act: -0.1700
Data Index: 8765599 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5388. Min Range: -12.5388
Max Act: 11.6638. Min Act: -0.1700
Data Index: 6978110 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5388. Min Range: -12.5388
Max Act: 11.6638. Min Act: -0.1700
Data Index: 8373538 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5388. Min Range: -12.5388
Max Act: 11.6013. Min Act: -0.1700
Data Index: 7094922 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5388. Min Range: -12.5388
Max Act: 11.5388. Min Act: -0.1700
Data Index: 6628797 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5388. Min Range: -12.5388
Max Act: 11.6013. Min Act: -0.1700
Data Index: 7775306 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5388. Min Range: -12.5388
Max Act: 11.4763. Min Act: -0.1700
Data Index: 8238792 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5388. Min Range: -12.5388
Max Act: 11.4138. Min Act: -0.1700
Data Index: 1031569 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5388. Min Range: -12.5388
Max Act: 11.4138. Min Act: -0.1700
Data Index: 6226675 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5388. Min Range: -12.5388
Max Act: 11.4138. Min Act: -0.1700
Data Index: 3036854 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5388. Min Range: -12.5388
Max Act: 11.4138. Min Act: -0.1700
Data Index: 3766508 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5388. Min Range: -12.5388
Max Act: 11.3513. Min Act: -0.1700
Data Index: 4159224 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5388. Min Range: -12.5388
Max Act: 11.2888. Min Act: -0.1700
Data Index: 7467858 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19