Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 790 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.3502. Min Act: -0.1700
Data Index: 5522804 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.1940. Min Act: -0.1700
Data Index: 609669 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.1940. Min Act: -0.1700
Data Index: 5246219 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.1627. Min Act: -0.1700
Data Index: 7438582 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.1627. Min Act: -0.1700
Data Index: 3345860 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.1627. Min Act: -0.1700
Data Index: 5782181 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.1002. Min Act: -0.1700
Data Index: 3429249 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.0690. Min Act: -0.1700
Data Index: 4974148 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.0690. Min Act: -0.1700
Data Index: 4898705 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.0377. Min Act: -0.1700
Data Index: 5884823 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.0377. Min Act: -0.1700
Data Index: 2748378 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.0690. Min Act: -0.1700
Data Index: 2911016 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.0065. Min Act: -0.1700
Data Index: 8045635 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.0065. Min Act: -0.1700
Data Index: 4542245 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.0065. Min Act: -0.1700
Data Index: 8226574 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.0065. Min Act: -0.1700
Data Index: 4713113 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.0065. Min Act: -0.1700
Data Index: 4550344 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.0065. Min Act: -0.1700
Data Index: 4550342 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3502. Min Range: -5.3502
Max Act: 5.0065. Min Act: -0.1700
Data Index: 974252 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3502. Min Range: -5.3502
Max Act: 4.9440. Min Act: -0.1700
Data Index: 5300626 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19