Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1972 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.6543. Min Act: -0.1700
Data Index: 5830427 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.5605. Min Act: -0.1700
Data Index: 6531103 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.4980. Min Act: -0.1700
Data Index: 6596749 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.4668. Min Act: -0.1700
Data Index: 128814 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.3105. Min Act: -0.1700
Data Index: 436000 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.3418. Min Act: -0.1700
Data Index: 595714 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.3418. Min Act: -0.1700
Data Index: 6835888 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.3105. Min Act: -0.1700
Data Index: 6550071 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.3105. Min Act: -0.1700
Data Index: 2958299 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.2793. Min Act: -0.1700
Data Index: 6280941 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.2793. Min Act: -0.1700
Data Index: 4971231 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.2793. Min Act: -0.1700
Data Index: 2361830 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.2793. Min Act: -0.1700
Data Index: 3735681 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.2480. Min Act: -0.1700
Data Index: 5657183 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.2480. Min Act: -0.1700
Data Index: 1053604 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.2480. Min Act: -0.1700
Data Index: 7158509 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.2480. Min Act: -0.1700
Data Index: 7469154 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.2168. Min Act: -0.1700
Data Index: 5458761 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.2168. Min Act: -0.1700
Data Index: 5421751 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6543. Min Range: -5.6543
Max Act: 5.2168. Min Act: -0.1700
Data Index: 3541868 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19