Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4404 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.8291. Min Act: -0.1700
Data Index: 6867651 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.7978. Min Act: -0.1700
Data Index: 5215802 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.7978. Min Act: -0.1700
Data Index: 6020991 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.7353. Min Act: -0.1700
Data Index: 8382161 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.7041. Min Act: -0.1700
Data Index: 653138 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.7041. Min Act: -0.1700
Data Index: 1452341 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.7041. Min Act: -0.1700
Data Index: 6483075 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.6728. Min Act: -0.1700
Data Index: 6020971 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.6416. Min Act: -0.1700
Data Index: 7055995 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.6416. Min Act: -0.1700
Data Index: 6483078 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.6728. Min Act: -0.1700
Data Index: 5683046 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.6416. Min Act: -0.1700
Data Index: 4706806 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.6416. Min Act: -0.1700
Data Index: 6483077 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.6103. Min Act: -0.1700
Data Index: 5995364 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.6416. Min Act: -0.1700
Data Index: 2380762 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.6103. Min Act: -0.1700
Data Index: 5683048 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.6103. Min Act: -0.1700
Data Index: 6340078 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.5791. Min Act: -0.1700
Data Index: 570348 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.5791. Min Act: -0.1700
Data Index: 3455179 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8291. Min Range: -4.8291
Max Act: 4.5791. Min Act: -0.1700
Data Index: 2003911 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19