Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2004. Min Range: -4.2004
Max Act: 4.2004. Min Act: -0.1700
Data Index: 42848 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2004. Min Range: -4.2004
Max Act: 4.0129. Min Act: -0.1700
Data Index: 4397792 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.9503. Min Act: -0.1700
Data Index: 1730547 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.8878. Min Act: -0.1700
Data Index: 8219327 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.8409. Min Act: -0.1700
Data Index: 3842993 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.8253. Min Act: -0.1700
Data Index: 1084068 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.8253. Min Act: -0.1700
Data Index: 7395639 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7940. Min Act: -0.1700
Data Index: 5630089 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.8096. Min Act: -0.1700
Data Index: 772872 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7471. Min Act: -0.1700
Data Index: 8642409 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7471. Min Act: -0.1700
Data Index: 8057714 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7471. Min Act: -0.1700
Data Index: 7420338 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7471. Min Act: -0.1700
Data Index: 5026206 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7471. Min Act: -0.1700
Data Index: 3491700 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7314. Min Act: -0.1700
Data Index: 3538194 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7314. Min Act: -0.1700
Data Index: 1080462 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7002. Min Act: -0.1700
Data Index: 1452837 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7314. Min Act: -0.1700
Data Index: 2844133 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7158. Min Act: -0.1700
Data Index: 2659907 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2004. Min Range: -4.2004
Max Act: 3.7314. Min Act: -0.1700
Data Index: 4611835 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19