Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2778 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.9421. Min Act: -0.1700
Data Index: 3578523 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.7858. Min Act: -0.1700
Data Index: 1681429 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.7546. Min Act: -0.1700
Data Index: 3092745 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.7546. Min Act: -0.1700
Data Index: 2915555 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.6921. Min Act: -0.1700
Data Index: 1100483 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.5671. Min Act: -0.1700
Data Index: 7941421 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.5358. Min Act: -0.1700
Data Index: 7812848 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.5671. Min Act: -0.1700
Data Index: 5481169 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.5358. Min Act: -0.1700
Data Index: 7902321 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.5671. Min Act: -0.1700
Data Index: 2847820 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.5358. Min Act: -0.1700
Data Index: 6439924 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.5671. Min Act: -0.1700
Data Index: 1900203 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.4421. Min Act: -0.1700
Data Index: 1631899 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.5046. Min Act: -0.1700
Data Index: 7305108 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.5046. Min Act: -0.1700
Data Index: 2052368 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.4733. Min Act: -0.1700
Data Index: 2459325 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.4733. Min Act: -0.1700
Data Index: 5158556 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.4421. Min Act: -0.1700
Data Index: 156990 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.4108. Min Act: -0.1700
Data Index: 6209986 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9421. Min Range: -6.9421
Max Act: 6.5046. Min Act: -0.1700
Data Index: 2503565 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19