Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3773 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3695. Min Range: -6.3695
Max Act: 6.3383. Min Act: -0.1700
Data Index: 1081001 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3695. Min Range: -6.3695
Max Act: 6.3695. Min Act: -0.1700
Data Index: 6598593 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3695. Min Range: -6.3695
Max Act: 6.2758. Min Act: -0.1700
Data Index: 2064399 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3695. Min Range: -6.3695
Max Act: 6.1820. Min Act: -0.1700
Data Index: 5039253 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3695. Min Range: -6.3695
Max Act: 6.1508. Min Act: -0.1700
Data Index: 4970100 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3695. Min Range: -6.3695
Max Act: 6.1508. Min Act: -0.1700
Data Index: 6544532 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3695. Min Range: -6.3695
Max Act: 6.0883. Min Act: -0.1700
Data Index: 2654625 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3695. Min Range: -6.3695
Max Act: 6.0570. Min Act: -0.1700
Data Index: 6885316 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3695. Min Range: -6.3695
Max Act: 6.0570. Min Act: -0.1700
Data Index: 1782575 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3695. Min Range: -6.3695
Max Act: 5.9945. Min Act: -0.1700
Data Index: 3458371 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3695. Min Range: -6.3695
Max Act: 5.9945. Min Act: -0.1700
Data Index: 2131745 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3695. Min Range: -6.3695
Max Act: 5.9633. Min Act: -0.1700
Data Index: 8702067 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3695. Min Range: -6.3695
Max Act: 5.9633. Min Act: -0.1700
Data Index: 7429270 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3695. Min Range: -6.3695
Max Act: 5.9633. Min Act: -0.1700
Data Index: 8314500 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3695. Min Range: -6.3695
Max Act: 5.9633. Min Act: -0.1700
Data Index: 5891670 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3695. Min Range: -6.3695
Max Act: 5.9945. Min Act: -0.1700
Data Index: 8315776 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3695. Min Range: -6.3695
Max Act: 5.9320. Min Act: -0.1700
Data Index: 4508062 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3695. Min Range: -6.3695
Max Act: 5.9008. Min Act: -0.1700
Data Index: 2713176 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3695. Min Range: -6.3695
Max Act: 5.9008. Min Act: -0.1700
Data Index: 7402950 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3695. Min Range: -6.3695
Max Act: 5.9008. Min Act: -0.1700
Data Index: 6193652 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19