Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1053 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1197. Min Range: -7.1197
Max Act: 7.1197. Min Act: -0.1700
Data Index: 1109720 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1197. Min Range: -7.1197
Max Act: 7.1197. Min Act: -0.1700
Data Index: 2357279 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1197. Min Range: -7.1197
Max Act: 7.0259. Min Act: -0.1700
Data Index: 700778 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1197. Min Range: -7.1197
Max Act: 7.0259. Min Act: -0.1700
Data Index: 7248176 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1197. Min Range: -7.1197
Max Act: 6.9009. Min Act: -0.1700
Data Index: 502845 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1197. Min Range: -7.1197
Max Act: 6.9322. Min Act: -0.1700
Data Index: 2587905 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1197. Min Range: -7.1197
Max Act: 6.7759. Min Act: -0.1700
Data Index: 8347908 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1197. Min Range: -7.1197
Max Act: 6.9009. Min Act: -0.1700
Data Index: 2012758 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1197. Min Range: -7.1197
Max Act: 6.8697. Min Act: -0.1700
Data Index: 5573845 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1197. Min Range: -7.1197
Max Act: 6.9009. Min Act: -0.1700
Data Index: 400098 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1197. Min Range: -7.1197
Max Act: 6.7759. Min Act: -0.1700
Data Index: 573152 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1197. Min Range: -7.1197
Max Act: 6.7759. Min Act: -0.1700
Data Index: 713700 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1197. Min Range: -7.1197
Max Act: 6.8384. Min Act: -0.1700
Data Index: 1334674 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1197. Min Range: -7.1197
Max Act: 6.7134. Min Act: -0.1700
Data Index: 3146262 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1197. Min Range: -7.1197
Max Act: 6.8384. Min Act: -0.1700
Data Index: 1730048 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1197. Min Range: -7.1197
Max Act: 6.7134. Min Act: -0.1700
Data Index: 4196554 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1197. Min Range: -7.1197
Max Act: 6.6822. Min Act: -0.1700
Data Index: 7081528 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1197. Min Range: -7.1197
Max Act: 6.6509. Min Act: -0.1700
Data Index: 7015127 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1197. Min Range: -7.1197
Max Act: 6.5259. Min Act: -0.1700
Data Index: 6836160 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1197. Min Range: -7.1197
Max Act: 6.5259. Min Act: -0.1700
Data Index: 2585570 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19