Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4194 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6632. Min Range: -7.6632
Max Act: 7.6632. Min Act: -0.1700
Data Index: 5308141 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6632. Min Range: -7.6632
Max Act: 7.3820. Min Act: -0.1700
Data Index: 8770953 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6632. Min Range: -7.6632
Max Act: 7.3195. Min Act: -0.1700
Data Index: 6857502 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6632. Min Range: -7.6632
Max Act: 7.0695. Min Act: -0.1700
Data Index: 2353348 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6632. Min Range: -7.6632
Max Act: 7.0695. Min Act: -0.1700
Data Index: 6287006 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6632. Min Range: -7.6632
Max Act: 7.0382. Min Act: -0.1700
Data Index: 3724046 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6632. Min Range: -7.6632
Max Act: 7.0382. Min Act: -0.1700
Data Index: 3113177 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6632. Min Range: -7.6632
Max Act: 6.9757. Min Act: -0.1700
Data Index: 7314152 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6632. Min Range: -7.6632
Max Act: 7.0070. Min Act: -0.1700
Data Index: 7872564 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6632. Min Range: -7.6632
Max Act: 7.0070. Min Act: -0.1700
Data Index: 8426210 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6632. Min Range: -7.6632
Max Act: 7.0070. Min Act: -0.1700
Data Index: 699655 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6632. Min Range: -7.6632
Max Act: 6.9757. Min Act: -0.1700
Data Index: 3410953 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6632. Min Range: -7.6632
Max Act: 6.9757. Min Act: -0.1700
Data Index: 4454045 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6632. Min Range: -7.6632
Max Act: 6.9132. Min Act: -0.1700
Data Index: 2848165 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6632. Min Range: -7.6632
Max Act: 6.9445. Min Act: -0.1700
Data Index: 5389769 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6632. Min Range: -7.6632
Max Act: 6.9445. Min Act: -0.1700
Data Index: 6122660 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6632. Min Range: -7.6632
Max Act: 6.9445. Min Act: -0.1700
Data Index: 6238661 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6632. Min Range: -7.6632
Max Act: 6.9445. Min Act: -0.1700
Data Index: 5250394 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6632. Min Range: -7.6632
Max Act: 6.9445. Min Act: -0.1700
Data Index: 1008714 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6632. Min Range: -7.6632
Max Act: 6.9445. Min Act: -0.1700
Data Index: 1747163 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19