Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1481 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.5388. Min Act: -0.1700
Data Index: 6720747 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.4451. Min Act: -0.1700
Data Index: 4659643 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.4138. Min Act: -0.1700
Data Index: 7295134 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.3826. Min Act: -0.1700
Data Index: 4117021 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.3513. Min Act: -0.1700
Data Index: 8600539 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.3513. Min Act: -0.1700
Data Index: 967595 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.3513. Min Act: -0.1700
Data Index: 2113735 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.3201. Min Act: -0.1700
Data Index: 8118440 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.3201. Min Act: -0.1700
Data Index: 7931062 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.3201. Min Act: -0.1700
Data Index: 7918536 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.3201. Min Act: -0.1700
Data Index: 8333412 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.3201. Min Act: -0.1700
Data Index: 2834648 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.2888. Min Act: -0.1700
Data Index: 2446739 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.2888. Min Act: -0.1700
Data Index: 5401254 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.2888. Min Act: -0.1700
Data Index: 4480624 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.2888. Min Act: -0.1700
Data Index: 1103343 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.2888. Min Act: -0.1700
Data Index: 4117017 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.2575. Min Act: -0.1700
Data Index: 721539 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.2575. Min Act: -0.1700
Data Index: 2607896 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5388. Min Range: -4.5388
Max Act: 4.2263. Min Act: -0.1700
Data Index: 5524745 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19