Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 541 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5885. Min Range: -6.5885
Max Act: 6.5885. Min Act: -0.1700
Data Index: 487709 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5885. Min Range: -6.5885
Max Act: 6.4322. Min Act: -0.1700
Data Index: 8679328 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5885. Min Range: -6.5885
Max Act: 6.3072. Min Act: -0.1700
Data Index: 8385470 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5885. Min Range: -6.5885
Max Act: 6.3072. Min Act: -0.1700
Data Index: 7566853 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5885. Min Range: -6.5885
Max Act: 6.3385. Min Act: -0.1700
Data Index: 3165607 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5885. Min Range: -6.5885
Max Act: 6.2760. Min Act: -0.1700
Data Index: 4274946 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5885. Min Range: -6.5885
Max Act: 6.2447. Min Act: -0.1700
Data Index: 5706795 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5885. Min Range: -6.5885
Max Act: 6.2135. Min Act: -0.1700
Data Index: 6542001 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5885. Min Range: -6.5885
Max Act: 6.2135. Min Act: -0.1700
Data Index: 2833262 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5885. Min Range: -6.5885
Max Act: 6.1510. Min Act: -0.1700
Data Index: 4856563 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5885. Min Range: -6.5885
Max Act: 6.1197. Min Act: -0.1700
Data Index: 4174109 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5885. Min Range: -6.5885
Max Act: 6.1197. Min Act: -0.1700
Data Index: 1554858 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5885. Min Range: -6.5885
Max Act: 6.1510. Min Act: -0.1700
Data Index: 3482207 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5885. Min Range: -6.5885
Max Act: 6.0885. Min Act: -0.1700
Data Index: 3040305 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5885. Min Range: -6.5885
Max Act: 6.0572. Min Act: -0.1700
Data Index: 6420449 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5885. Min Range: -6.5885
Max Act: 6.0572. Min Act: -0.1700
Data Index: 20582 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5885. Min Range: -6.5885
Max Act: 6.0572. Min Act: -0.1700
Data Index: 6250023 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5885. Min Range: -6.5885
Max Act: 5.9947. Min Act: -0.1700
Data Index: 44483 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5885. Min Range: -6.5885
Max Act: 5.9947. Min Act: -0.1700
Data Index: 2340095 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5885. Min Range: -6.5885
Max Act: 5.9635. Min Act: -0.1700
Data Index: 5422823 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19