Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3958 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0585. Min Range: -5.0585
Max Act: 5.0585. Min Act: -0.1700
Data Index: 8731578 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9960. Min Act: -0.1700
Data Index: 6797603 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9960. Min Act: -0.1700
Data Index: 353158 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9960. Min Act: -0.1700
Data Index: 935572 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9960. Min Act: -0.1700
Data Index: 211091 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9648. Min Act: -0.1700
Data Index: 7620630 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9335. Min Act: -0.1700
Data Index: 4624553 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9335. Min Act: -0.1700
Data Index: 1831852 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9648. Min Act: -0.1700
Data Index: 8083772 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9335. Min Act: -0.1700
Data Index: 2166458 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9335. Min Act: -0.1700
Data Index: 5828531 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9335. Min Act: -0.1700
Data Index: 3505966 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9335. Min Act: -0.1700
Data Index: 1830747 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9023. Min Act: -0.1700
Data Index: 6739804 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9023. Min Act: -0.1700
Data Index: 1683444 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9335. Min Act: -0.1700
Data Index: 5399337 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9023. Min Act: -0.1700
Data Index: 5199004 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9335. Min Act: -0.1700
Data Index: 7604009 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.9335. Min Act: -0.1700
Data Index: 3525419 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0585. Min Range: -5.0585
Max Act: 4.8710. Min Act: -0.1700
Data Index: 3447314 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19