Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2464 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.2386. Min Act: -0.1700
Data Index: 6502102 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.2072. Min Act: -0.1700
Data Index: 4123536 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.0970. Min Act: -0.1700
Data Index: 1675058 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.0655. Min Act: -0.1700
Data Index: 6491017 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.0339. Min Act: -0.1700
Data Index: 1516263 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.0812. Min Act: -0.1700
Data Index: 332931 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.1128. Min Act: -0.1700
Data Index: 8013337 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.0497. Min Act: -0.1700
Data Index: 6772187 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.0655. Min Act: -0.1700
Data Index: 6160504 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.0497. Min Act: -0.1700
Data Index: 3181736 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.0181. Min Act: -0.1700
Data Index: 170175 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.0181. Min Act: -0.1700
Data Index: 6734512 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.0181. Min Act: -0.1700
Data Index: 579368 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.0181. Min Act: -0.1700
Data Index: 2258444 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.0181. Min Act: -0.1700
Data Index: 4775957 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.0023. Min Act: -0.1700
Data Index: 1046383 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.0181. Min Act: -0.1700
Data Index: 5258479 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.0181. Min Act: -0.1700
Data Index: 5033570 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.0181. Min Act: -0.1700
Data Index: 949770 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2386. Min Range: -3.2386
Max Act: 3.0339. Min Act: -0.1700
Data Index: 397130 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19