Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 489 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0234. Min Range: -2.0234
Max Act: 2.0234. Min Act: -0.1700
Data Index: 5717416 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0234. Min Range: -2.0234
Max Act: 2.0234. Min Act: -0.1700
Data Index: 4891026 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0234. Min Range: -2.0234
Max Act: 2.0065. Min Act: -0.1700
Data Index: 5827516 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0234. Min Range: -2.0234
Max Act: 1.9727. Min Act: -0.1700
Data Index: 6199971 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0234. Min Range: -2.0234
Max Act: 1.9558. Min Act: -0.1700
Data Index: 3036992 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0234. Min Range: -2.0234
Max Act: 1.9727. Min Act: -0.1700
Data Index: 1425805 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0234. Min Range: -2.0234
Max Act: 1.9727. Min Act: -0.1700
Data Index: 1154687 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0234. Min Range: -2.0234
Max Act: 1.9727. Min Act: -0.1700
Data Index: 7500838 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0234. Min Range: -2.0234
Max Act: 1.9727. Min Act: -0.1700
Data Index: 7085193 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0234. Min Range: -2.0234
Max Act: 1.9727. Min Act: -0.1700
Data Index: 784084 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0234. Min Range: -2.0234
Max Act: 1.9558. Min Act: -0.1700
Data Index: 7540370 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0234. Min Range: -2.0234
Max Act: 1.9558. Min Act: -0.1700
Data Index: 5822059 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0234. Min Range: -2.0234
Max Act: 1.9558. Min Act: -0.1700
Data Index: 2445623 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0234. Min Range: -2.0234
Max Act: 1.9558. Min Act: -0.1700
Data Index: 6787794 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0234. Min Range: -2.0234
Max Act: 1.9558. Min Act: -0.1700
Data Index: 2905552 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0234. Min Range: -2.0234
Max Act: 1.9388. Min Act: -0.1700
Data Index: 2070858 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0234. Min Range: -2.0234
Max Act: 1.9388. Min Act: -0.1700
Data Index: 5480626 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0234. Min Range: -2.0234
Max Act: 1.9388. Min Act: -0.1700
Data Index: 5717417 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0234. Min Range: -2.0234
Max Act: 1.9388. Min Act: -0.1700
Data Index: 5780027 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0234. Min Range: -2.0234
Max Act: 1.9388. Min Act: -0.1700
Data Index: 250367 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19