Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 75 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.3210. Min Act: -0.1700
Data Index: 7466165 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.1960. Min Act: -0.1700
Data Index: 7612270 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.1960. Min Act: -0.1700
Data Index: 5175453 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.1335. Min Act: -0.1700
Data Index: 6954847 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.1335. Min Act: -0.1700
Data Index: 6157363 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.1335. Min Act: -0.1700
Data Index: 1936558 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.1335. Min Act: -0.1700
Data Index: 2932231 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.1022. Min Act: -0.1700
Data Index: 4889565 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.1022. Min Act: -0.1700
Data Index: 1591274 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.1022. Min Act: -0.1700
Data Index: 7303305 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.1022. Min Act: -0.1700
Data Index: 2395391 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.0397. Min Act: -0.1700
Data Index: 2257312 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.1022. Min Act: -0.1700
Data Index: 994239 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.1022. Min Act: -0.1700
Data Index: 6553707 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.0710. Min Act: -0.1700
Data Index: 2801269 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.0397. Min Act: -0.1700
Data Index: 838784 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.0710. Min Act: -0.1700
Data Index: 2266988 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.0710. Min Act: -0.1700
Data Index: 309731 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.0397. Min Act: -0.1700
Data Index: 5068786 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.0085. Min Act: -0.1700
Data Index: 5882050 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19