Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2893 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3066. Min Range: -7.3066
Max Act: 7.3066. Min Act: -0.1700
Data Index: 934741 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3066. Min Range: -7.3066
Max Act: 7.0566. Min Act: -0.1700
Data Index: 934745 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3066. Min Range: -7.3066
Max Act: 7.0566. Min Act: -0.1700
Data Index: 2537028 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3066. Min Range: -7.3066
Max Act: 7.0253. Min Act: -0.1700
Data Index: 3490771 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3066. Min Range: -7.3066
Max Act: 6.9941. Min Act: -0.1700
Data Index: 1003135 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3066. Min Range: -7.3066
Max Act: 6.9941. Min Act: -0.1700
Data Index: 1254235 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3066. Min Range: -7.3066
Max Act: 6.9941. Min Act: -0.1700
Data Index: 1587823 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3066. Min Range: -7.3066
Max Act: 6.9628. Min Act: -0.1700
Data Index: 5885866 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3066. Min Range: -7.3066
Max Act: 6.9628. Min Act: -0.1700
Data Index: 8210177 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3066. Min Range: -7.3066
Max Act: 6.9628. Min Act: -0.1700
Data Index: 7556740 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3066. Min Range: -7.3066
Max Act: 6.9628. Min Act: -0.1700
Data Index: 5729740 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3066. Min Range: -7.3066
Max Act: 6.9003. Min Act: -0.1700
Data Index: 578291 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3066. Min Range: -7.3066
Max Act: 6.9003. Min Act: -0.1700
Data Index: 7556739 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3066. Min Range: -7.3066
Max Act: 6.9003. Min Act: -0.1700
Data Index: 2928222 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3066. Min Range: -7.3066
Max Act: 6.9003. Min Act: -0.1700
Data Index: 3842694 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3066. Min Range: -7.3066
Max Act: 6.9003. Min Act: -0.1700
Data Index: 7733357 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3066. Min Range: -7.3066
Max Act: 6.9003. Min Act: -0.1700
Data Index: 8098928 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3066. Min Range: -7.3066
Max Act: 6.9003. Min Act: -0.1700
Data Index: 2969167 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3066. Min Range: -7.3066
Max Act: 6.8691. Min Act: -0.1700
Data Index: 1224360 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3066. Min Range: -7.3066
Max Act: 6.8691. Min Act: -0.1700
Data Index: 1488795 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19