Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2832 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0097. Min Range: -3.0097
Max Act: 3.0097. Min Act: -0.1700
Data Index: 2944629 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.9781. Min Act: -0.1700
Data Index: 8412798 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.9781. Min Act: -0.1700
Data Index: 5814008 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.9781. Min Act: -0.1700
Data Index: 3748989 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.8989. Min Act: -0.1700
Data Index: 630379 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.9306. Min Act: -0.1700
Data Index: 993187 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.9148. Min Act: -0.1700
Data Index: 5096665 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.9148. Min Act: -0.1700
Data Index: 2946189 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.8830. Min Act: -0.1700
Data Index: 1447202 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.8830. Min Act: -0.1700
Data Index: 5186356 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.8672. Min Act: -0.1700
Data Index: 2044255 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.8672. Min Act: -0.1700
Data Index: 1319344 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.8830. Min Act: -0.1700
Data Index: 3102863 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.8513. Min Act: -0.1700
Data Index: 5351095 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.8672. Min Act: -0.1700
Data Index: 4455315 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.8513. Min Act: -0.1700
Data Index: 3932878 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.8513. Min Act: -0.1700
Data Index: 4803168 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.8513. Min Act: -0.1700
Data Index: 49694 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.8354. Min Act: -0.1700
Data Index: 6160873 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0097. Min Range: -3.0097
Max Act: 2.8513. Min Act: -0.1700
Data Index: 4532104 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19