Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5094 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.9335. Min Act: -0.1700
Data Index: 6458123 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.7460. Min Act: -0.1700
Data Index: 1952916 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.6210. Min Act: -0.1700
Data Index: 467282 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.5585. Min Act: -0.1700
Data Index: 2886849 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.5585. Min Act: -0.1700
Data Index: 7029428 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.5585. Min Act: -0.1700
Data Index: 467274 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.4960. Min Act: -0.1700
Data Index: 941487 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.4960. Min Act: -0.1700
Data Index: 7718638 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.4335. Min Act: -0.1700
Data Index: 1530469 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.4335. Min Act: -0.1700
Data Index: 891476 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.3085. Min Act: -0.1700
Data Index: 6290908 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.3085. Min Act: -0.1700
Data Index: 3138795 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.3085. Min Act: -0.1700
Data Index: 889909 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.3085. Min Act: -0.1700
Data Index: 7910848 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.3085. Min Act: -0.1700
Data Index: 4202583 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.3085. Min Act: -0.1700
Data Index: 4269773 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.3085. Min Act: -0.1700
Data Index: 4519499 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.2460. Min Act: -0.1700
Data Index: 1952918 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.2460. Min Act: -0.1700
Data Index: 594864 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9335. Min Range: -8.9335
Max Act: 8.2460. Min Act: -0.1700
Data Index: 4883036 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19