Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.5189. Min Act: -0.1700
Data Index: 6199077 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.4251. Min Act: -0.1700
Data Index: 4114233 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.3939. Min Act: -0.1700
Data Index: 4003942 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.3626. Min Act: -0.1700
Data Index: 3103784 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.3314. Min Act: -0.1700
Data Index: 4003943 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.3001. Min Act: -0.1700
Data Index: 6381938 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.3001. Min Act: -0.1700
Data Index: 8682041 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.3001. Min Act: -0.1700
Data Index: 5564335 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.2689. Min Act: -0.1700
Data Index: 7131721 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.2689. Min Act: -0.1700
Data Index: 4650750 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.2689. Min Act: -0.1700
Data Index: 4008167 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.2689. Min Act: -0.1700
Data Index: 6862378 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.2689. Min Act: -0.1700
Data Index: 6724018 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.2689. Min Act: -0.1700
Data Index: 6381940 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.2376. Min Act: -0.1700
Data Index: 4003944 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.2689. Min Act: -0.1700
Data Index: 8450366 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.2376. Min Act: -0.1700
Data Index: 3860032 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.2689. Min Act: -0.1700
Data Index: 8682040 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.2689. Min Act: -0.1700
Data Index: 122812 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.2376. Min Act: -0.1700
Data Index: 122814 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19