Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5575 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3309. Min Range: -6.3309
Max Act: 6.3309. Min Act: -0.1700
Data Index: 3863812 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3309. Min Range: -6.3309
Max Act: 6.2372. Min Act: -0.1700
Data Index: 4503173 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3309. Min Range: -6.3309
Max Act: 6.2372. Min Act: -0.1700
Data Index: 3687226 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3309. Min Range: -6.3309
Max Act: 6.0809. Min Act: -0.1700
Data Index: 5741581 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3309. Min Range: -6.3309
Max Act: 5.9872. Min Act: -0.1700
Data Index: 3673861 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3309. Min Range: -6.3309
Max Act: 6.0497. Min Act: -0.1700
Data Index: 3967596 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3309. Min Range: -6.3309
Max Act: 5.9559. Min Act: -0.1700
Data Index: 2770373 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3309. Min Range: -6.3309
Max Act: 5.9559. Min Act: -0.1700
Data Index: 4331072 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3309. Min Range: -6.3309
Max Act: 5.9559. Min Act: -0.1700
Data Index: 8741481 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3309. Min Range: -6.3309
Max Act: 5.9247. Min Act: -0.1700
Data Index: 2212254 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3309. Min Range: -6.3309
Max Act: 5.8934. Min Act: -0.1700
Data Index: 7371770 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3309. Min Range: -6.3309
Max Act: 5.8934. Min Act: -0.1700
Data Index: 7690715 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3309. Min Range: -6.3309
Max Act: 5.8934. Min Act: -0.1700
Data Index: 331400 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3309. Min Range: -6.3309
Max Act: 5.8934. Min Act: -0.1700
Data Index: 780457 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3309. Min Range: -6.3309
Max Act: 5.8934. Min Act: -0.1700
Data Index: 1201007 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3309. Min Range: -6.3309
Max Act: 5.8934. Min Act: -0.1700
Data Index: 491925 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3309. Min Range: -6.3309
Max Act: 5.8622. Min Act: -0.1700
Data Index: 684574 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3309. Min Range: -6.3309
Max Act: 5.8622. Min Act: -0.1700
Data Index: 4088848 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3309. Min Range: -6.3309
Max Act: 5.8622. Min Act: -0.1700
Data Index: 8480373 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3309. Min Range: -6.3309
Max Act: 5.8622. Min Act: -0.1700
Data Index: 7622096 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19