Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1694 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.4595. Min Act: -0.1700
Data Index: 1092611 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.4282. Min Act: -0.1700
Data Index: 1097183 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.3657. Min Act: -0.1700
Data Index: 4572836 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.3345. Min Act: -0.1700
Data Index: 6759489 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.2095. Min Act: -0.1700
Data Index: 5330687 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.1470. Min Act: -0.1700
Data Index: 8776867 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.2095. Min Act: -0.1700
Data Index: 7781263 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.1782. Min Act: -0.1700
Data Index: 455256 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.1782. Min Act: -0.1700
Data Index: 6751081 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.1470. Min Act: -0.1700
Data Index: 3545194 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.0845. Min Act: -0.1700
Data Index: 1896134 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.1157. Min Act: -0.1700
Data Index: 4066005 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.1157. Min Act: -0.1700
Data Index: 6469984 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.1157. Min Act: -0.1700
Data Index: 5456630 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.1157. Min Act: -0.1700
Data Index: 380219 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.1157. Min Act: -0.1700
Data Index: 8270577 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.0845. Min Act: -0.1700
Data Index: 1999762 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.0845. Min Act: -0.1700
Data Index: 6669074 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.0845. Min Act: -0.1700
Data Index: 5230719 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4595. Min Range: -5.4595
Max Act: 5.0532. Min Act: -0.1700
Data Index: 2610734 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19