Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 545 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8182. Min Range: -7.8182
Max Act: 7.8182. Min Act: -0.1700
Data Index: 3694198 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8182. Min Range: -7.8182
Max Act: 7.1307. Min Act: -0.1700
Data Index: 4920776 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8182. Min Range: -7.8182
Max Act: 7.0995. Min Act: -0.1700
Data Index: 2624140 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8182. Min Range: -7.8182
Max Act: 7.0370. Min Act: -0.1700
Data Index: 2160171 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8182. Min Range: -7.8182
Max Act: 7.0057. Min Act: -0.1700
Data Index: 8544764 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8182. Min Range: -7.8182
Max Act: 6.9432. Min Act: -0.1700
Data Index: 2001344 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8182. Min Range: -7.8182
Max Act: 6.8182. Min Act: -0.1700
Data Index: 8652261 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8182. Min Range: -7.8182
Max Act: 6.7870. Min Act: -0.1700
Data Index: 6609721 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8182. Min Range: -7.8182
Max Act: 6.7870. Min Act: -0.1700
Data Index: 1361814 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8182. Min Range: -7.8182
Max Act: 6.7557. Min Act: -0.1700
Data Index: 5777853 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8182. Min Range: -7.8182
Max Act: 6.5995. Min Act: -0.1700
Data Index: 1720991 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8182. Min Range: -7.8182
Max Act: 6.6932. Min Act: -0.1700
Data Index: 4920775 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8182. Min Range: -7.8182
Max Act: 6.6620. Min Act: -0.1700
Data Index: 3694188 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8182. Min Range: -7.8182
Max Act: 6.5682. Min Act: -0.1700
Data Index: 4648614 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8182. Min Range: -7.8182
Max Act: 6.6307. Min Act: -0.1700
Data Index: 4920777 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8182. Min Range: -7.8182
Max Act: 6.6307. Min Act: -0.1700
Data Index: 8544757 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8182. Min Range: -7.8182
Max Act: 6.5370. Min Act: -0.1700
Data Index: 2464190 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8182. Min Range: -7.8182
Max Act: 6.5682. Min Act: -0.1700
Data Index: 3502258 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8182. Min Range: -7.8182
Max Act: 6.5995. Min Act: -0.1700
Data Index: 5736057 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8182. Min Range: -7.8182
Max Act: 6.5370. Min Act: -0.1700
Data Index: 8194513 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19