Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4263 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2952. Min Range: -7.2952
Max Act: 7.2952. Min Act: -0.1700
Data Index: 5698170 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2952. Min Range: -7.2952
Max Act: 7.2327. Min Act: -0.1700
Data Index: 1066844 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2952. Min Range: -7.2952
Max Act: 7.1077. Min Act: -0.1700
Data Index: 3393186 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2952. Min Range: -7.2952
Max Act: 7.1389. Min Act: -0.1700
Data Index: 6275773 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2952. Min Range: -7.2952
Max Act: 7.1077. Min Act: -0.1700
Data Index: 5011625 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2952. Min Range: -7.2952
Max Act: 7.1077. Min Act: -0.1700
Data Index: 8237074 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2952. Min Range: -7.2952
Max Act: 7.0452. Min Act: -0.1700
Data Index: 2431158 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2952. Min Range: -7.2952
Max Act: 6.9202. Min Act: -0.1700
Data Index: 8349041 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2952. Min Range: -7.2952
Max Act: 6.8889. Min Act: -0.1700
Data Index: 1113307 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2952. Min Range: -7.2952
Max Act: 6.8889. Min Act: -0.1700
Data Index: 7163293 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2952. Min Range: -7.2952
Max Act: 6.8577. Min Act: -0.1700
Data Index: 8412495 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2952. Min Range: -7.2952
Max Act: 6.8577. Min Act: -0.1700
Data Index: 4429135 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2952. Min Range: -7.2952
Max Act: 6.8577. Min Act: -0.1700
Data Index: 3691197 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2952. Min Range: -7.2952
Max Act: 6.7952. Min Act: -0.1700
Data Index: 4913408 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2952. Min Range: -7.2952
Max Act: 6.7952. Min Act: -0.1700
Data Index: 6920160 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2952. Min Range: -7.2952
Max Act: 6.7952. Min Act: -0.1700
Data Index: 2447512 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2952. Min Range: -7.2952
Max Act: 6.7639. Min Act: -0.1700
Data Index: 6748886 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2952. Min Range: -7.2952
Max Act: 6.7639. Min Act: -0.1700
Data Index: 625692 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2952. Min Range: -7.2952
Max Act: 6.7327. Min Act: -0.1700
Data Index: 3806692 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2952. Min Range: -7.2952
Max Act: 6.7327. Min Act: -0.1700
Data Index: 6600906 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19