Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 551 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.3794. Min Act: -0.1700
Data Index: 835903 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.3009. Min Act: -0.1700
Data Index: 173077 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.3166. Min Act: -0.1700
Data Index: 714740 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.3009. Min Act: -0.1700
Data Index: 4268501 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.2695. Min Act: -0.1700
Data Index: 5010342 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.2381. Min Act: -0.1700
Data Index: 5499764 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.2538. Min Act: -0.1700
Data Index: 7389300 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.2538. Min Act: -0.1700
Data Index: 4279069 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.2538. Min Act: -0.1700
Data Index: 5245014 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.2538. Min Act: -0.1700
Data Index: 7840529 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.2538. Min Act: -0.1700
Data Index: 4398694 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.2538. Min Act: -0.1700
Data Index: 3260216 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.2538. Min Act: -0.1700
Data Index: 8636341 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.2067. Min Act: -0.1700
Data Index: 5437464 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.2067. Min Act: -0.1700
Data Index: 3959782 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.2224. Min Act: -0.1700
Data Index: 269510 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.2224. Min Act: -0.1700
Data Index: 3419646 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.2067. Min Act: -0.1700
Data Index: 7590813 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.2224. Min Act: -0.1700
Data Index: 7716811 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3794. Min Range: -3.3794
Max Act: 3.2067. Min Act: -0.1700
Data Index: 1957225 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19