Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2488 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.9542. Min Act: -0.1700
Data Index: 8533847 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.9229. Min Act: -0.1700
Data Index: 888254 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.9229. Min Act: -0.1700
Data Index: 7058916 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.8604. Min Act: -0.1700
Data Index: 1573032 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.8604. Min Act: -0.1700
Data Index: 1773714 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.8292. Min Act: -0.1700
Data Index: 8482878 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.7979. Min Act: -0.1700
Data Index: 3505054 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.7979. Min Act: -0.1700
Data Index: 7250089 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.7979. Min Act: -0.1700
Data Index: 7429486 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.7979. Min Act: -0.1700
Data Index: 616161 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.7979. Min Act: -0.1700
Data Index: 7802145 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.7667. Min Act: -0.1700
Data Index: 1930289 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.7667. Min Act: -0.1700
Data Index: 5676360 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.7667. Min Act: -0.1699
Data Index: 2263596 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.7354. Min Act: -0.1700
Data Index: 883512 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.7667. Min Act: -0.1700
Data Index: 5237061 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.7042. Min Act: -0.1700
Data Index: 2568150 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.7354. Min Act: -0.1700
Data Index: 8275586 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.7042. Min Act: -0.1700
Data Index: 3076643 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9542. Min Range: -6.9542
Max Act: 6.7042. Min Act: -0.1700
Data Index: 6463194 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19