Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2329 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.4892. Min Act: -0.1700
Data Index: 3697169 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.3329. Min Act: -0.1700
Data Index: 5728264 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.3016. Min Act: -0.1700
Data Index: 3539778 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.3016. Min Act: -0.1700
Data Index: 3278990 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.2704. Min Act: -0.1700
Data Index: 6519210 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.2704. Min Act: -0.1700
Data Index: 357180 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.2391. Min Act: -0.1700
Data Index: 7041132 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.2391. Min Act: -0.1700
Data Index: 4467497 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.2391. Min Act: -0.1700
Data Index: 1244828 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.2079. Min Act: -0.1700
Data Index: 1547362 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.2079. Min Act: -0.1700
Data Index: 1626991 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.2079. Min Act: -0.1700
Data Index: 4052286 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.2079. Min Act: -0.1700
Data Index: 3829551 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.2079. Min Act: -0.1700
Data Index: 4370201 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.2079. Min Act: -0.1700
Data Index: 3767095 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.2079. Min Act: -0.1700
Data Index: 3765655 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.2079. Min Act: -0.1700
Data Index: 4332782 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.1454. Min Act: -0.1700
Data Index: 4169301 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.1454. Min Act: -0.1700
Data Index: 2842578 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4892. Min Range: -4.4892
Max Act: 4.1454. Min Act: -0.1700
Data Index: 5002508 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19