Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3364 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1799. Min Range: -10.1799
Max Act: 10.1799. Min Act: -0.1700
Data Index: 3774550 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.7424. Min Act: -0.1700
Data Index: 7710045 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.6174. Min Act: -0.1700
Data Index: 3522085 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.6174. Min Act: -0.1700
Data Index: 2972600 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.6174. Min Act: -0.1700
Data Index: 5696015 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.5549. Min Act: -0.1700
Data Index: 8252247 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.6174. Min Act: -0.1700
Data Index: 566354 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.5549. Min Act: -0.1700
Data Index: 5901085 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.4924. Min Act: -0.1700
Data Index: 3345970 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.3674. Min Act: -0.1700
Data Index: 8382433 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.4299. Min Act: -0.1700
Data Index: 1740723 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.4299. Min Act: -0.1700
Data Index: 7040090 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.4299. Min Act: -0.1700
Data Index: 2244918 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.4299. Min Act: -0.1700
Data Index: 2792187 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.3674. Min Act: -0.1700
Data Index: 4656806 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.3674. Min Act: -0.1700
Data Index: 945783 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.2424. Min Act: -0.1700
Data Index: 7885600 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.3049. Min Act: -0.1700
Data Index: 5514979 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.3049. Min Act: -0.1700
Data Index: 5050707 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1799. Min Range: -10.1799
Max Act: 9.3049. Min Act: -0.1700
Data Index: 6603069 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19