Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1436 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.4482. Min Act: -0.1697
Data Index: 1275155 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.3545. Min Act: -0.1700
Data Index: 8109311 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.3232. Min Act: -0.1700
Data Index: 7771168 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.2295. Min Act: -0.1700
Data Index: 7406800 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.2295. Min Act: -0.1700
Data Index: 6657880 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.2295. Min Act: -0.1700
Data Index: 3310474 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.1982. Min Act: -0.1700
Data Index: 6021528 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.1670. Min Act: -0.1700
Data Index: 4436273 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.1670. Min Act: -0.1700
Data Index: 998831 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.1045. Min Act: -0.1700
Data Index: 5152466 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.0732. Min Act: -0.1700
Data Index: 3992571 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.1045. Min Act: -0.1700
Data Index: 6850058 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.0420. Min Act: -0.1700
Data Index: 7993945 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.0420. Min Act: -0.1700
Data Index: 6977653 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.0420. Min Act: -0.1700
Data Index: 3882729 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.0107. Min Act: -0.1700
Data Index: 1275146 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.0107. Min Act: -0.1700
Data Index: 5198573 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4482. Min Range: -5.4482
Max Act: 4.9795. Min Act: -0.1700
Data Index: 2937992 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.0107. Min Act: -0.1700
Data Index: 6570134 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4482. Min Range: -5.4482
Max Act: 5.0420. Min Act: -0.1700
Data Index: 5702015 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19