Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1840 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7979. Min Range: -5.7979
Max Act: 5.7979. Min Act: -0.1700
Data Index: 4453671 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7979. Min Range: -5.7979
Max Act: 5.0167. Min Act: -0.1700
Data Index: 4200948 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.9542. Min Act: -0.1700
Data Index: 8662547 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.9542. Min Act: -0.1700
Data Index: 7313028 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.8292. Min Act: -0.1700
Data Index: 4699836 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.8604. Min Act: -0.1700
Data Index: 5864336 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.8292. Min Act: -0.1700
Data Index: 3972353 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.8604. Min Act: -0.1700
Data Index: 3682456 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.8604. Min Act: -0.1700
Data Index: 2216058 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.8292. Min Act: -0.1700
Data Index: 5493240 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.7979. Min Act: -0.1700
Data Index: 3699677 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.7979. Min Act: -0.1700
Data Index: 119708 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.7979. Min Act: -0.1700
Data Index: 2321660 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.7979. Min Act: -0.1700
Data Index: 1969307 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.7979. Min Act: -0.1700
Data Index: 6497117 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.7667. Min Act: -0.1700
Data Index: 65567 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.7667. Min Act: -0.1700
Data Index: 4676978 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.7667. Min Act: -0.1700
Data Index: 8520420 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.7667. Min Act: -0.1700
Data Index: 1910571 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7979. Min Range: -5.7979
Max Act: 4.7667. Min Act: -0.1700
Data Index: 8767801 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19