Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 749 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.8122. Min Act: -0.1700
Data Index: 6280027 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.6247. Min Act: -0.1700
Data Index: 8251080 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.6247. Min Act: -0.1700
Data Index: 4587215 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.5934. Min Act: -0.1700
Data Index: 7129063 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.6247. Min Act: -0.1700
Data Index: 8276295 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.6559. Min Act: -0.1700
Data Index: 3733290 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.5309. Min Act: -0.1700
Data Index: 3525620 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.5309. Min Act: -0.1700
Data Index: 8470915 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.4372. Min Act: -0.1700
Data Index: 3778351 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.4059. Min Act: -0.1700
Data Index: 7158616 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.4059. Min Act: -0.1700
Data Index: 5712306 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.4059. Min Act: -0.1700
Data Index: 2870363 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.3747. Min Act: -0.1700
Data Index: 1256070 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.3747. Min Act: -0.1700
Data Index: 2966401 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.3122. Min Act: -0.1700
Data Index: 2954141 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.3122. Min Act: -0.1700
Data Index: 252440 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.3122. Min Act: -0.1700
Data Index: 7847583 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.3122. Min Act: -0.1700
Data Index: 3452002 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.3122. Min Act: -0.1700
Data Index: 8342764 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8122. Min Range: -6.8122
Max Act: 6.2809. Min Act: -0.1700
Data Index: 6968421 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19