Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1826 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.8084. Min Act: -0.1700
Data Index: 5825632 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.8084. Min Act: -0.1700
Data Index: 4688935 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.6834. Min Act: -0.1700
Data Index: 5471646 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.6209. Min Act: -0.1700
Data Index: 8810461 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.3397. Min Act: -0.1700
Data Index: 7904073 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.3084. Min Act: -0.1700
Data Index: 4684827 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.3397. Min Act: -0.1700
Data Index: 2172791 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.2772. Min Act: -0.1700
Data Index: 6400771 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.2772. Min Act: -0.1700
Data Index: 7341478 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.2459. Min Act: -0.1700
Data Index: 1844373 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.1834. Min Act: -0.1700
Data Index: 1298461 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.1522. Min Act: -0.1700
Data Index: 3955653 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.0897. Min Act: -0.1700
Data Index: 4308226 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.0897. Min Act: -0.1700
Data Index: 1082848 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.0897. Min Act: -0.1700
Data Index: 4346530 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.0584. Min Act: -0.1700
Data Index: 582226 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.0897. Min Act: -0.1700
Data Index: 5354296 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.0584. Min Act: -0.1700
Data Index: 3394171 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.0584. Min Act: -0.1700
Data Index: 7075257 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8084. Min Range: -7.8084
Max Act: 7.0272. Min Act: -0.1700
Data Index: 7026197 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19