Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3516 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2927. Min Range: -6.2927
Max Act: 6.2927. Min Act: -0.1700
Data Index: 2106586 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.9177. Min Act: -0.1700
Data Index: 3625345 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.8239. Min Act: -0.1700
Data Index: 7164870 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.7927. Min Act: -0.1700
Data Index: 2552214 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.7614. Min Act: -0.1700
Data Index: 5018238 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.7302. Min Act: -0.1700
Data Index: 8680133 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.6989. Min Act: -0.1700
Data Index: 6891069 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.6364. Min Act: -0.1700
Data Index: 6589275 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.6364. Min Act: -0.1700
Data Index: 42905 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.6052. Min Act: -0.1700
Data Index: 5055858 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.5739. Min Act: -0.1700
Data Index: 4240571 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.5739. Min Act: -0.1700
Data Index: 2545621 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.5739. Min Act: -0.1700
Data Index: 6812674 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.5114. Min Act: -0.1700
Data Index: 1372901 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.5114. Min Act: -0.1700
Data Index: 7132550 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.4489. Min Act: -0.1700
Data Index: 2558114 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.4177. Min Act: -0.1700
Data Index: 191254 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.4489. Min Act: -0.1700
Data Index: 2591144 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.4489. Min Act: -0.1700
Data Index: 5489064 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2927. Min Range: -6.2927
Max Act: 5.4177. Min Act: -0.1700
Data Index: 1946751 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19