Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4500 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.3537. Min Act: -0.1700
Data Index: 4018929 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.3225. Min Act: -0.1700
Data Index: 3191000 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.1037. Min Act: -0.1700
Data Index: 2808068 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.1037. Min Act: -0.1700
Data Index: 872978 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3537. Min Range: -5.3537
Max Act: 5.0725. Min Act: -0.1700
Data Index: 8326677 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3537. Min Range: -5.3537
Max Act: 4.9787. Min Act: -0.1700
Data Index: 754281 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3537. Min Range: -5.3537
Max Act: 4.9787. Min Act: -0.1700
Data Index: 2234441 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3537. Min Range: -5.3537
Max Act: 4.9475. Min Act: -0.1700
Data Index: 4226673 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3537. Min Range: -5.3537
Max Act: 4.9162. Min Act: -0.1700
Data Index: 340138 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3537. Min Range: -5.3537
Max Act: 4.8537. Min Act: -0.1700
Data Index: 1350289 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3537. Min Range: -5.3537
Max Act: 4.8850. Min Act: -0.1700
Data Index: 8735035 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3537. Min Range: -5.3537
Max Act: 4.8225. Min Act: -0.1700
Data Index: 5735331 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3537. Min Range: -5.3537
Max Act: 4.8225. Min Act: -0.1700
Data Index: 1953001 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3537. Min Range: -5.3537
Max Act: 4.7912. Min Act: -0.1700
Data Index: 5860592 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3537. Min Range: -5.3537
Max Act: 4.7912. Min Act: -0.1700
Data Index: 8730845 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3537. Min Range: -5.3537
Max Act: 4.7912. Min Act: -0.1700
Data Index: 5825888 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3537. Min Range: -5.3537
Max Act: 4.7912. Min Act: -0.1700
Data Index: 5509460 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3537. Min Range: -5.3537
Max Act: 4.7600. Min Act: -0.1700
Data Index: 2032040 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3537. Min Range: -5.3537
Max Act: 4.7287. Min Act: -0.1700
Data Index: 3122878 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3537. Min Range: -5.3537
Max Act: 4.7287. Min Act: -0.1700
Data Index: 3030956 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19