Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2468 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.8575. Min Act: -0.1700
Data Index: 4514652 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.3409. Min Act: -0.1700
Data Index: 6311787 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.3566. Min Act: -0.1700
Data Index: 6014916 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.3095. Min Act: -0.1700
Data Index: 6547577 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.2938. Min Act: -0.1700
Data Index: 7027398 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.1995. Min Act: -0.1700
Data Index: 4896142 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.1680. Min Act: -0.1700
Data Index: 798403 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.1208. Min Act: -0.1700
Data Index: 3356794 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.1523. Min Act: -0.1700
Data Index: 2075820 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.1366. Min Act: -0.1700
Data Index: 4082152 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.0893. Min Act: -0.1700
Data Index: 4590215 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.1208. Min Act: -0.1700
Data Index: 6639748 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.1051. Min Act: -0.1700
Data Index: 2274367 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.0577. Min Act: -0.1700
Data Index: 7298008 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.0893. Min Act: -0.1700
Data Index: 5903756 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.0577. Min Act: -0.1700
Data Index: 5824315 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.0577. Min Act: -0.1700
Data Index: 4448637 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.0577. Min Act: -0.1700
Data Index: 7128583 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.0420. Min Act: -0.1700
Data Index: 4158514 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8575. Min Range: -3.8575
Max Act: 3.0262. Min Act: -0.1700
Data Index: 5656196 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19