Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4073 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.4866. Min Act: -0.1700
Data Index: 7333502 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.3726. Min Act: -0.1700
Data Index: 6552515 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.3562. Min Act: -0.1700
Data Index: 7840941 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.3398. Min Act: -0.1700
Data Index: 6342057 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.3398. Min Act: -0.1700
Data Index: 1646189 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.3398. Min Act: -0.1700
Data Index: 4143603 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.3070. Min Act: -0.1700
Data Index: 8221198 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.3234. Min Act: -0.1700
Data Index: 5579771 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.2905. Min Act: -0.1700
Data Index: 6793688 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.2905. Min Act: -0.1700
Data Index: 4036295 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.3070. Min Act: -0.1700
Data Index: 5135841 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.2905. Min Act: -0.1700
Data Index: 7629475 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.2905. Min Act: -0.1700
Data Index: 807592 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.2905. Min Act: -0.1700
Data Index: 3246515 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.2905. Min Act: -0.1700
Data Index: 2841227 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.2575. Min Act: -0.1700
Data Index: 370851 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.2740. Min Act: -0.1700
Data Index: 8383906 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.2740. Min Act: -0.1700
Data Index: 2022738 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.2740. Min Act: -0.1700
Data Index: 3317855 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4866. Min Range: -2.4866
Max Act: 2.2740. Min Act: -0.1700
Data Index: 881899 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19