Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3753 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.4469. Min Act: -0.1700
Data Index: 6387061 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.4156. Min Act: -0.1700
Data Index: 7833816 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.4156. Min Act: -0.1700
Data Index: 6387055 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.3842. Min Act: -0.1700
Data Index: 7347915 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.3842. Min Act: -0.1700
Data Index: 7124029 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.3529. Min Act: -0.1700
Data Index: 7590723 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.3529. Min Act: -0.1700
Data Index: 5434289 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.3529. Min Act: -0.1700
Data Index: 4468712 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.3529. Min Act: -0.1700
Data Index: 7064719 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.3215. Min Act: -0.1700
Data Index: 7234645 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.3215. Min Act: -0.1700
Data Index: 1195750 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.3215. Min Act: -0.1700
Data Index: 8071171 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.3215. Min Act: -0.1700
Data Index: 6324329 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.3215. Min Act: -0.1700
Data Index: 3737861 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.3215. Min Act: -0.1700
Data Index: 723234 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.2901. Min Act: -0.1700
Data Index: 7185882 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.2901. Min Act: -0.1700
Data Index: 1843994 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.2901. Min Act: -0.1700
Data Index: 3713789 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.2901. Min Act: -0.1700
Data Index: 944198 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4469. Min Range: -3.4469
Max Act: 3.2901. Min Act: -0.1700
Data Index: 6386791 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19