Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2019 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.8757. Min Act: -0.1700
Data Index: 2242614 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.8757. Min Act: -0.1700
Data Index: 3380998 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.8288. Min Act: -0.1700
Data Index: 847837 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.8445. Min Act: -0.1700
Data Index: 1190133 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.7819. Min Act: -0.1700
Data Index: 4187128 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.7819. Min Act: -0.1700
Data Index: 1541223 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.7350. Min Act: -0.1700
Data Index: 7429191 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.7194. Min Act: -0.1700
Data Index: 1496127 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.7194. Min Act: -0.1700
Data Index: 8121868 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.7350. Min Act: -0.1700
Data Index: 619462 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.7194. Min Act: -0.1700
Data Index: 3653099 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.6881. Min Act: -0.1700
Data Index: 4272810 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.6881. Min Act: -0.1700
Data Index: 1614 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.6881. Min Act: -0.1700
Data Index: 211614 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.6411. Min Act: -0.1700
Data Index: 1062131 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.6411. Min Act: -0.1700
Data Index: 7680890 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.6411. Min Act: -0.1700
Data Index: 2751712 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.6411. Min Act: -0.1700
Data Index: 4335817 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.6255. Min Act: -0.1700
Data Index: 2728181 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8757. Min Range: -3.8757
Max Act: 3.6411. Min Act: -0.1700
Data Index: 3983195 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19