Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2703 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1159. Min Range: -5.1159
Max Act: 5.1159. Min Act: -0.1700
Data Index: 2629154 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.9909. Min Act: -0.1700
Data Index: 988030 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.9909. Min Act: -0.1700
Data Index: 6261322 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.9597. Min Act: -0.1700
Data Index: 5209568 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.9597. Min Act: -0.1700
Data Index: 5014566 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.9284. Min Act: -0.1700
Data Index: 1396023 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.8972. Min Act: -0.1700
Data Index: 7340397 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.8659. Min Act: -0.1700
Data Index: 8616254 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.8972. Min Act: -0.1700
Data Index: 3954456 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.8972. Min Act: -0.1700
Data Index: 5289322 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.8972. Min Act: -0.1700
Data Index: 4133711 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.8659. Min Act: -0.1700
Data Index: 3156966 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.8659. Min Act: -0.1700
Data Index: 5704353 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.8347. Min Act: -0.1700
Data Index: 2675733 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.8659. Min Act: -0.1700
Data Index: 5079518 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.8659. Min Act: -0.1700
Data Index: 1049104 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.7722. Min Act: -0.1700
Data Index: 4693554 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.8034. Min Act: -0.1700
Data Index: 4741131 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.8034. Min Act: -0.1700
Data Index: 4141152 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1159. Min Range: -5.1159
Max Act: 4.8034. Min Act: -0.1700
Data Index: 4062022 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19