Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2644 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.7782. Min Act: -0.1700
Data Index: 4454344 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.6844. Min Act: -0.1700
Data Index: 4419930 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.6844. Min Act: -0.1700
Data Index: 7682313 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.6219. Min Act: -0.1700
Data Index: 402797 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.6219. Min Act: -0.1700
Data Index: 18349 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.6219. Min Act: -0.1700
Data Index: 692579 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.5907. Min Act: -0.1700
Data Index: 207205 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.4969. Min Act: -0.1700
Data Index: 8731968 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.4344. Min Act: -0.1700
Data Index: 2212108 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.4657. Min Act: -0.1700
Data Index: 6852611 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.4344. Min Act: -0.1700
Data Index: 1189521 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.4032. Min Act: -0.1700
Data Index: 8690583 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.3719. Min Act: -0.1700
Data Index: 3637552 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.3407. Min Act: -0.1700
Data Index: 7173159 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.3407. Min Act: -0.1700
Data Index: 382465 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.2782. Min Act: -0.1700
Data Index: 8641987 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.2782. Min Act: -0.1700
Data Index: 592735 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.2469. Min Act: -0.1700
Data Index: 6230687 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.2469. Min Act: -0.1700
Data Index: 7358731 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.2157. Min Act: -0.1700
Data Index: 8155528 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19