Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2939 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.3604. Min Act: -0.1700
Data Index: 2449625 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.0166. Min Act: -0.1700
Data Index: 4458178 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.8916. Min Act: -0.1700
Data Index: 8466440 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.8604. Min Act: -0.1700
Data Index: 5152626 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.8916. Min Act: -0.1700
Data Index: 6783729 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.7979. Min Act: -0.1700
Data Index: 396371 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.7666. Min Act: -0.1700
Data Index: 1865966 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.7354. Min Act: -0.1700
Data Index: 6254938 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.7354. Min Act: -0.1700
Data Index: 5192349 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.7041. Min Act: -0.1700
Data Index: 2394647 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.7354. Min Act: -0.1700
Data Index: 4496637 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.7354. Min Act: -0.1700
Data Index: 72877 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.7041. Min Act: -0.1700
Data Index: 3685826 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.6416. Min Act: -0.1700
Data Index: 8629578 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.6729. Min Act: -0.1700
Data Index: 1626125 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.6729. Min Act: -0.1700
Data Index: 8538656 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.6729. Min Act: -0.1700
Data Index: 8322444 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.6416. Min Act: -0.1700
Data Index: 4604370 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.6416. Min Act: -0.1700
Data Index: 2726877 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3604. Min Range: -5.3604
Max Act: 4.6416. Min Act: -0.1700
Data Index: 7969338 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19