Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.6152. Min Act: -0.1700
Data Index: 3679623 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.4902. Min Act: -0.1700
Data Index: 5706240 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.4277. Min Act: -0.1700
Data Index: 5705104 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.3652. Min Act: -0.1700
Data Index: 8659473 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.3652. Min Act: -0.1700
Data Index: 2898718 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.3340. Min Act: -0.1700
Data Index: 5706276 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.3340. Min Act: -0.1700
Data Index: 1171435 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.3340. Min Act: -0.1700
Data Index: 6377939 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.2715. Min Act: -0.1700
Data Index: 7559395 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.2402. Min Act: -0.1700
Data Index: 2535789 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.1777. Min Act: -0.1700
Data Index: 6534394 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.2090. Min Act: -0.1700
Data Index: 1679139 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.1777. Min Act: -0.1700
Data Index: 3570077 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.1777. Min Act: -0.1700
Data Index: 2155440 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.1777. Min Act: -0.1700
Data Index: 6355589 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.1465. Min Act: -0.1700
Data Index: 2706320 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.1152. Min Act: -0.1700
Data Index: 2043470 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.1152. Min Act: -0.1700
Data Index: 7592473 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.1152. Min Act: -0.1700
Data Index: 1436150 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6152. Min Range: -5.6152
Max Act: 5.1152. Min Act: -0.1700
Data Index: 2387614 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19