Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4935 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.5006. Min Act: -0.1700
Data Index: 4841621 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.4381. Min Act: -0.1700
Data Index: 6750683 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.4069. Min Act: -0.1700
Data Index: 168884 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.3131. Min Act: -0.1700
Data Index: 5673064 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.3131. Min Act: -0.1700
Data Index: 1420675 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.3131. Min Act: -0.1700
Data Index: 7486466 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.3131. Min Act: -0.1700
Data Index: 1041648 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.2506. Min Act: -0.1700
Data Index: 5438919 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.2506. Min Act: -0.1700
Data Index: 8076974 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.2194. Min Act: -0.1700
Data Index: 5438920 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.2194. Min Act: -0.1700
Data Index: 2591199 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.2194. Min Act: -0.1700
Data Index: 6893495 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.2194. Min Act: -0.1700
Data Index: 7145090 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.2194. Min Act: -0.1700
Data Index: 8038477 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.2194. Min Act: -0.1700
Data Index: 7847008 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.2194. Min Act: -0.1700
Data Index: 6634839 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.2194. Min Act: -0.1700
Data Index: 4757115 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.1881. Min Act: -0.1700
Data Index: 7828308 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.1881. Min Act: -0.1700
Data Index: 1041652 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5006. Min Range: -4.5006
Max Act: 4.1568. Min Act: -0.1700
Data Index: 607850 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19