Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3181 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.3534. Min Act: -0.1700
Data Index: 839897 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.2909. Min Act: -0.1700
Data Index: 5961920 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.1972. Min Act: -0.1700
Data Index: 3316716 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.1659. Min Act: -0.1700
Data Index: 4079661 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.1347. Min Act: -0.1700
Data Index: 4125392 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.1034. Min Act: -0.1700
Data Index: 5702701 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.1034. Min Act: -0.1700
Data Index: 1620223 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.0722. Min Act: -0.1700
Data Index: 438910 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.0722. Min Act: -0.1700
Data Index: 3205074 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.0722. Min Act: -0.1700
Data Index: 8131416 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.0409. Min Act: -0.1700
Data Index: 3174063 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.0409. Min Act: -0.1700
Data Index: 7079793 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.0409. Min Act: -0.1700
Data Index: 1032451 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.0409. Min Act: -0.1700
Data Index: 4863166 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.0409. Min Act: -0.1700
Data Index: 2941200 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.0097. Min Act: -0.1700
Data Index: 4902854 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.0097. Min Act: -0.1700
Data Index: 5917411 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.0097. Min Act: -0.1700
Data Index: 6253672 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.0097. Min Act: -0.1700
Data Index: 922345 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3534. Min Range: -5.3534
Max Act: 5.0097. Min Act: -0.1700
Data Index: 5564116 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19