Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3523 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.1566. Min Act: -0.1700
Data Index: 2704089 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.1566. Min Act: -0.1700
Data Index: 6605029 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.1566. Min Act: -0.1700
Data Index: 7586059 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.1253. Min Act: -0.1700
Data Index: 6425482 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.1253. Min Act: -0.1700
Data Index: 6548929 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.1253. Min Act: -0.1700
Data Index: 3105813 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.1253. Min Act: -0.1700
Data Index: 4921519 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.1253. Min Act: -0.1700
Data Index: 7326681 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.0941. Min Act: -0.1700
Data Index: 5721182 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.0941. Min Act: -0.1700
Data Index: 6677467 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.0941. Min Act: -0.1700
Data Index: 189591 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.0628. Min Act: -0.1700
Data Index: 2601644 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.0628. Min Act: -0.1700
Data Index: 6393368 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.0628. Min Act: -0.1700
Data Index: 7493664 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.0628. Min Act: -0.1700
Data Index: 4422861 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.0628. Min Act: -0.1700
Data Index: 7208981 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.0628. Min Act: -0.1700
Data Index: 1360825 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.0628. Min Act: -0.1700
Data Index: 333637 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.0628. Min Act: -0.1700
Data Index: 614490 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1566. Min Range: -5.1566
Max Act: 5.0628. Min Act: -0.1700
Data Index: 1413198 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19