Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1231 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.5524. Min Act: -0.1700
Data Index: 2953927 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.5524. Min Act: -0.1700
Data Index: 2902830 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.5211. Min Act: -0.1700
Data Index: 5427368 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.4899. Min Act: -0.1700
Data Index: 385251 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.5211. Min Act: -0.1700
Data Index: 7247120 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.4899. Min Act: -0.1700
Data Index: 7551547 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.4899. Min Act: -0.1700
Data Index: 5005087 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.4586. Min Act: -0.1700
Data Index: 5408208 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.4586. Min Act: -0.1700
Data Index: 6212147 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.4586. Min Act: -0.1700
Data Index: 5305775 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.4586. Min Act: -0.1700
Data Index: 1621504 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.4586. Min Act: -0.1700
Data Index: 936072 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.4274. Min Act: -0.1700
Data Index: 5352309 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.4274. Min Act: -0.1700
Data Index: 830113 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.3961. Min Act: -0.1700
Data Index: 2452171 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.3961. Min Act: -0.1700
Data Index: 173715 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.3649. Min Act: -0.1700
Data Index: 2955058 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.3961. Min Act: -0.1700
Data Index: 7090391 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.3961. Min Act: -0.1700
Data Index: 1795979 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.3649. Min Act: -0.1700
Data Index: 7091548 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19