Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 69 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.8956. Min Act: -0.1700
Data Index: 1776286 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.8331. Min Act: -0.1700
Data Index: 6408912 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.8331. Min Act: -0.1700
Data Index: 4533444 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.8331. Min Act: -0.1700
Data Index: 3570443 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.7706. Min Act: -0.1700
Data Index: 4969272 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.6456. Min Act: -0.1700
Data Index: 4546152 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.6456. Min Act: -0.1700
Data Index: 877919 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.6456. Min Act: -0.1700
Data Index: 694204 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.5206. Min Act: -0.1700
Data Index: 6933805 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.4268. Min Act: -0.1700
Data Index: 404366 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.4268. Min Act: -0.1700
Data Index: 915271 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.4581. Min Act: -0.1700
Data Index: 1709429 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.4581. Min Act: -0.1700
Data Index: 6795059 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.4268. Min Act: -0.1700
Data Index: 6765061 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.4268. Min Act: -0.1700
Data Index: 2521198 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.4268. Min Act: -0.1700
Data Index: 3087070 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.3956. Min Act: -0.1700
Data Index: 4991789 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.3956. Min Act: -0.1700
Data Index: 4757263 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.3956. Min Act: -0.1700
Data Index: 3508288 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8956. Min Range: -7.8956
Max Act: 7.3956. Min Act: -0.1700
Data Index: 5971087 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19