Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3135 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3918. Min Range: -5.3918
Max Act: 5.3918. Min Act: -0.1700
Data Index: 5485343 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3918. Min Range: -5.3918
Max Act: 5.1418. Min Act: -0.1700
Data Index: 6153182 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3918. Min Range: -5.3918
Max Act: 5.1105. Min Act: -0.1700
Data Index: 5194573 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3918. Min Range: -5.3918
Max Act: 5.1105. Min Act: -0.1700
Data Index: 7906160 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3918. Min Range: -5.3918
Max Act: 5.0793. Min Act: -0.1700
Data Index: 5452084 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3918. Min Range: -5.3918
Max Act: 5.0480. Min Act: -0.1700
Data Index: 5730955 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3918. Min Range: -5.3918
Max Act: 5.0168. Min Act: -0.1700
Data Index: 4025990 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3918. Min Range: -5.3918
Max Act: 5.0168. Min Act: -0.1700
Data Index: 6816262 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3918. Min Range: -5.3918
Max Act: 4.9855. Min Act: -0.1700
Data Index: 91896 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3918. Min Range: -5.3918
Max Act: 4.9543. Min Act: -0.1700
Data Index: 2617636 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3918. Min Range: -5.3918
Max Act: 4.9230. Min Act: -0.1700
Data Index: 7776807 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3918. Min Range: -5.3918
Max Act: 4.9543. Min Act: -0.1700
Data Index: 4294359 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3918. Min Range: -5.3918
Max Act: 4.9230. Min Act: -0.1700
Data Index: 4025132 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3918. Min Range: -5.3918
Max Act: 4.9230. Min Act: -0.1700
Data Index: 8276727 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3918. Min Range: -5.3918
Max Act: 4.9230. Min Act: -0.1700
Data Index: 1282762 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3918. Min Range: -5.3918
Max Act: 4.8918. Min Act: -0.1700
Data Index: 6068733 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3918. Min Range: -5.3918
Max Act: 4.8918. Min Act: -0.1700
Data Index: 7373232 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3918. Min Range: -5.3918
Max Act: 4.8918. Min Act: -0.1700
Data Index: 845720 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3918. Min Range: -5.3918
Max Act: 4.8605. Min Act: -0.1700
Data Index: 2491965 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3918. Min Range: -5.3918
Max Act: 4.8918. Min Act: -0.1700
Data Index: 2466834 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19