Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1734 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0411. Min Range: -7.0411
Max Act: 7.0411. Min Act: -0.1700
Data Index: 4973401 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0411. Min Range: -7.0411
Max Act: 7.0099. Min Act: -0.1700
Data Index: 3108810 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.8224. Min Act: -0.1700
Data Index: 4862027 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.7286. Min Act: -0.1700
Data Index: 1286289 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.6661. Min Act: -0.1700
Data Index: 6807356 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.6661. Min Act: -0.1700
Data Index: 6229922 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.5724. Min Act: -0.1700
Data Index: 5347721 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.5099. Min Act: -0.1700
Data Index: 4408895 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.5411. Min Act: -0.1700
Data Index: 8713949 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.5099. Min Act: -0.1700
Data Index: 1058407 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.4786. Min Act: -0.1700
Data Index: 6110001 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.4474. Min Act: -0.1700
Data Index: 5034561 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.3849. Min Act: -0.1700
Data Index: 6113333 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.3224. Min Act: -0.1700
Data Index: 3194805 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.3224. Min Act: -0.1700
Data Index: 4736869 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.3224. Min Act: -0.1700
Data Index: 2880554 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.2911. Min Act: -0.1700
Data Index: 7853913 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.2911. Min Act: -0.1700
Data Index: 2100968 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.2911. Min Act: -0.1700
Data Index: 5327536 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0411. Min Range: -7.0411
Max Act: 6.2286. Min Act: -0.1700
Data Index: 5700643 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19