Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1105 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.7196. Min Act: -0.1700
Data Index: 6316661 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.7196. Min Act: -0.1700
Data Index: 6210893 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.7196. Min Act: -0.1700
Data Index: 4237933 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.6571. Min Act: -0.1700
Data Index: 5725910 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.6259. Min Act: -0.1700
Data Index: 2605701 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.5009. Min Act: -0.1700
Data Index: 6277259 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.5321. Min Act: -0.1700
Data Index: 3552308 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.5009. Min Act: -0.1700
Data Index: 6523433 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.5009. Min Act: -0.1700
Data Index: 3341336 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.5009. Min Act: -0.1700
Data Index: 3745368 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.4696. Min Act: -0.1700
Data Index: 5138517 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.4696. Min Act: -0.1700
Data Index: 6367607 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.4696. Min Act: -0.1700
Data Index: 3856209 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.4384. Min Act: -0.1700
Data Index: 3892541 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.4384. Min Act: -0.1700
Data Index: 4858060 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.4384. Min Act: -0.1700
Data Index: 1648881 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.4071. Min Act: -0.1700
Data Index: 5143107 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.4384. Min Act: -0.1700
Data Index: 5730473 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.4071. Min Act: -0.1700
Data Index: 2092601 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7196. Min Range: -4.7196
Max Act: 4.4071. Min Act: -0.1700
Data Index: 3726491 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19