Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5263 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2087. Min Range: -7.2087
Max Act: 7.2087. Min Act: -0.1700
Data Index: 5260251 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2087. Min Range: -7.2087
Max Act: 7.0525. Min Act: -0.1700
Data Index: 7137462 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2087. Min Range: -7.2087
Max Act: 7.0212. Min Act: -0.1700
Data Index: 7535828 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.9900. Min Act: -0.1700
Data Index: 1140577 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.9900. Min Act: -0.1700
Data Index: 8588069 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.9587. Min Act: -0.1700
Data Index: 1128372 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.9587. Min Act: -0.1700
Data Index: 494810 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.8962. Min Act: -0.1700
Data Index: 1047925 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.8650. Min Act: -0.1700
Data Index: 6239711 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.8337. Min Act: -0.1700
Data Index: 5813728 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.8650. Min Act: -0.1700
Data Index: 3779530 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.8337. Min Act: -0.1700
Data Index: 7251479 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.8337. Min Act: -0.1700
Data Index: 919454 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.8337. Min Act: -0.1700
Data Index: 6531330 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.7712. Min Act: -0.1700
Data Index: 5518397 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.7400. Min Act: -0.1700
Data Index: 1105111 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.7400. Min Act: -0.1700
Data Index: 2842738 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.7400. Min Act: -0.1700
Data Index: 6399615 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.7087. Min Act: -0.1700
Data Index: 1723937 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2087. Min Range: -7.2087
Max Act: 6.7400. Min Act: -0.1700
Data Index: 2621525 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19