Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.4325. Min Act: -0.1700
Data Index: 2995651 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.4325. Min Act: -0.1700
Data Index: 6417409 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.4325. Min Act: -0.1700
Data Index: 1264965 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.4012. Min Act: -0.1698
Data Index: 7459371 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.4012. Min Act: -0.1700
Data Index: 3448627 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.4012. Min Act: -0.1700
Data Index: 3322766 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.4012. Min Act: -0.1700
Data Index: 5018568 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.4012. Min Act: -0.1699
Data Index: 760785 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.3700. Min Act: -0.1700
Data Index: 7627824 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.3700. Min Act: -0.1700
Data Index: 138517 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.3700. Min Act: -0.1700
Data Index: 11371 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.3700. Min Act: -0.1700
Data Index: 1425512 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.3387. Min Act: -0.1700
Data Index: 5534021 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.3075. Min Act: -0.1698
Data Index: 4974101 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.3075. Min Act: -0.1700
Data Index: 6160097 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.3387. Min Act: -0.1700
Data Index: 3583505 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.3387. Min Act: -0.1700
Data Index: 1346336 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.3387. Min Act: -0.1700
Data Index: 3575269 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.3387. Min Act: -0.1700
Data Index: 1411944 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.3387. Min Act: -0.1700
Data Index: 5785328 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19