Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4476 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7733. Min Act: -0.1700
Data Index: 607825 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7733. Min Act: -0.1700
Data Index: 8569277 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7420. Min Act: -0.1700
Data Index: 2807151 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7733. Min Act: -0.1700
Data Index: 3560660 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7420. Min Act: -0.1700
Data Index: 5748984 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7420. Min Act: -0.1700
Data Index: 5738198 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7108. Min Act: -0.1700
Data Index: 1002745 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7420. Min Act: -0.1700
Data Index: 497659 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7420. Min Act: -0.1700
Data Index: 5634546 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7420. Min Act: -0.1700
Data Index: 195994 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7420. Min Act: -0.1700
Data Index: 3656274 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7420. Min Act: -0.1700
Data Index: 4276678 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7733. Min Act: -0.1700
Data Index: 4601277 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7108. Min Act: -0.1700
Data Index: 2744262 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7108. Min Act: -0.1700
Data Index: 534958 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7108. Min Act: -0.1700
Data Index: 1620569 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7108. Min Act: -0.1700
Data Index: 3344344 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7108. Min Act: -0.1700
Data Index: 3150448 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7108. Min Act: -0.1700
Data Index: 216812 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7733. Min Range: -4.7733
Max Act: 4.7108. Min Act: -0.1700
Data Index: 3065813 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19