Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 578 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.8680. Min Act: -0.1700
Data Index: 1442534 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.7118. Min Act: -0.1700
Data Index: 1357456 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.6180. Min Act: -0.1700
Data Index: 1357448 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.5243. Min Act: -0.1700
Data Index: 1442522 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.5243. Min Act: -0.1700
Data Index: 3300247 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.4618. Min Act: -0.1700
Data Index: 703837 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.4618. Min Act: -0.1700
Data Index: 3300264 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.3993. Min Act: -0.1700
Data Index: 1357443 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.3993. Min Act: -0.1700
Data Index: 7151029 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.3680. Min Act: -0.1700
Data Index: 703834 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.3680. Min Act: -0.1700
Data Index: 1357444 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.3368. Min Act: -0.1700
Data Index: 510512 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.3368. Min Act: -0.1700
Data Index: 3158339 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.3368. Min Act: -0.1700
Data Index: 1357452 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.3055. Min Act: -0.1700
Data Index: 1943849 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.3055. Min Act: -0.1700
Data Index: 703839 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.3055. Min Act: -0.1700
Data Index: 510501 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.3055. Min Act: -0.1700
Data Index: 2514155 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.2743. Min Act: -0.1700
Data Index: 1943856 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8680. Min Range: -6.8680
Max Act: 6.2743. Min Act: -0.1700
Data Index: 703836 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19