Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3033 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7336. Min Range: -9.7336
Max Act: 9.7336. Min Act: -0.1700
Data Index: 1383803 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7336. Min Range: -9.7336
Max Act: 9.2961. Min Act: -0.1700
Data Index: 843349 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7336. Min Range: -9.7336
Max Act: 9.2336. Min Act: -0.1700
Data Index: 6255008 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7336. Min Range: -9.7336
Max Act: 9.1711. Min Act: -0.1700
Data Index: 5397619 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7336. Min Range: -9.7336
Max Act: 9.1711. Min Act: -0.1700
Data Index: 4702508 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7336. Min Range: -9.7336
Max Act: 8.8586. Min Act: -0.1700
Data Index: 5398639 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7336. Min Range: -9.7336
Max Act: 8.9211. Min Act: -0.1700
Data Index: 8093489 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7336. Min Range: -9.7336
Max Act: 8.8586. Min Act: -0.1700
Data Index: 1615165 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7336. Min Range: -9.7336
Max Act: 8.9211. Min Act: -0.1700
Data Index: 945057 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7336. Min Range: -9.7336
Max Act: 8.4211. Min Act: -0.1700
Data Index: 253939 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7336. Min Range: -9.7336
Max Act: 8.3586. Min Act: -0.1700
Data Index: 4538295 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7336. Min Range: -9.7336
Max Act: 8.3586. Min Act: -0.1700
Data Index: 2366556 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7336. Min Range: -9.7336
Max Act: 8.3586. Min Act: -0.1700
Data Index: 114362 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7336. Min Range: -9.7336
Max Act: 8.2961. Min Act: -0.1700
Data Index: 90229 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7336. Min Range: -9.7336
Max Act: 8.3586. Min Act: -0.1700
Data Index: 1202545 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7336. Min Range: -9.7336
Max Act: 8.2961. Min Act: -0.1700
Data Index: 2011793 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7336. Min Range: -9.7336
Max Act: 8.2961. Min Act: -0.1700
Data Index: 7817024 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7336. Min Range: -9.7336
Max Act: 8.2961. Min Act: -0.1700
Data Index: 6981595 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7336. Min Range: -9.7336
Max Act: 8.2336. Min Act: -0.1700
Data Index: 4006541 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7336. Min Range: -9.7336
Max Act: 8.2961. Min Act: -0.1700
Data Index: 3447591 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19