Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4184 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.6699. Min Act: -0.1700
Data Index: 867006 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.5136. Min Act: -0.1700
Data Index: 6543653 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.5136. Min Act: -0.1700
Data Index: 3408927 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.5136. Min Act: -0.1700
Data Index: 6284398 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.4511. Min Act: -0.1700
Data Index: 3639538 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.4511. Min Act: -0.1700
Data Index: 1653960 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.4199. Min Act: -0.1700
Data Index: 7385594 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.3574. Min Act: -0.1700
Data Index: 7890236 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.3261. Min Act: -0.1700
Data Index: 3470695 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.3261. Min Act: -0.1700
Data Index: 6219578 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2949. Min Act: -0.1700
Data Index: 2037982 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2949. Min Act: -0.1700
Data Index: 3850915 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2949. Min Act: -0.1700
Data Index: 17798 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2324. Min Act: -0.1700
Data Index: 3857003 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2949. Min Act: -0.1700
Data Index: 7337499 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2324. Min Act: -0.1700
Data Index: 2799446 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2011. Min Act: -0.1700
Data Index: 3970529 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2011. Min Act: -0.1700
Data Index: 7864605 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2011. Min Act: -0.1700
Data Index: 6972093 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.1699. Min Act: -0.1700
Data Index: 3524679 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19