Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 835 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0543. Min Range: -7.0543
Max Act: 7.0543. Min Act: -0.1700
Data Index: 3947873 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.6480. Min Act: -0.1700
Data Index: 3309122 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.6480. Min Act: -0.1700
Data Index: 2968041 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.6168. Min Act: -0.1700
Data Index: 3932541 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.6168. Min Act: -0.1700
Data Index: 5876916 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.5855. Min Act: -0.1700
Data Index: 6646331 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.5543. Min Act: -0.1700
Data Index: 5301717 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.6168. Min Act: -0.1700
Data Index: 6604952 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.5855. Min Act: -0.1700
Data Index: 2065715 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.5855. Min Act: -0.1700
Data Index: 6716325 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.5855. Min Act: -0.1700
Data Index: 1393537 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.5855. Min Act: -0.1700
Data Index: 3985032 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.5543. Min Act: -0.1700
Data Index: 6242371 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.5543. Min Act: -0.1700
Data Index: 8670172 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.5230. Min Act: -0.1700
Data Index: 7349657 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.5230. Min Act: -0.1700
Data Index: 6513801 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.5543. Min Act: -0.1700
Data Index: 6870697 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.5230. Min Act: -0.1700
Data Index: 885274 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.5230. Min Act: -0.1700
Data Index: 6709718 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0543. Min Range: -7.0543
Max Act: 6.5230. Min Act: -0.1700
Data Index: 4600537 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19