Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1003 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.8946. Min Act: -0.1700
Data Index: 3440093 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.7851. Min Act: -0.1700
Data Index: 7333463 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.7695. Min Act: -0.1700
Data Index: 4674355 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.7538. Min Act: -0.1700
Data Index: 133871 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.7695. Min Act: -0.1700
Data Index: 3210117 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.7538. Min Act: -0.1700
Data Index: 292454 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.7538. Min Act: -0.1700
Data Index: 3322020 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.7226. Min Act: -0.1700
Data Index: 8457854 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.7069. Min Act: -0.1700
Data Index: 517605 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.6913. Min Act: -0.1700
Data Index: 2792487 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.6756. Min Act: -0.1700
Data Index: 6501483 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.6130. Min Act: -0.1700
Data Index: 1296898 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.5974. Min Act: -0.1700
Data Index: 4329357 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.5817. Min Act: -0.1700
Data Index: 1681359 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.5504. Min Act: -0.1700
Data Index: 2508881 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.5348. Min Act: -0.1700
Data Index: 3475423 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.5191. Min Act: -0.1700
Data Index: 4618289 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.5191. Min Act: -0.1700
Data Index: 4180604 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.5035. Min Act: -0.1700
Data Index: 2282889 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8946. Min Range: -3.8946
Max Act: 3.5035. Min Act: -0.1700
Data Index: 4556710 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19