Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.8467. Min Act: -0.1700
Data Index: 5414055 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7842. Min Act: -0.1700
Data Index: 5450074 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7530. Min Act: -0.1700
Data Index: 5414053 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7217. Min Act: -0.1700
Data Index: 5414057 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7217. Min Act: -0.1700
Data Index: 427518 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.6905. Min Act: -0.1700
Data Index: 5414056 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.6905. Min Act: -0.1700
Data Index: 142464 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.6592. Min Act: -0.1700
Data Index: 53352 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.6280. Min Act: -0.1700
Data Index: 1884423 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.6280. Min Act: -0.1700
Data Index: 5414054 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5967. Min Act: -0.1700
Data Index: 5944460 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5655. Min Act: -0.1700
Data Index: 4358461 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5655. Min Act: -0.1700
Data Index: 4423439 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5655. Min Act: -0.1700
Data Index: 1729094 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5655. Min Act: -0.1700
Data Index: 3900086 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5342. Min Act: -0.1700
Data Index: 179937 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5030. Min Act: -0.1700
Data Index: 2755426 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5342. Min Act: -0.1700
Data Index: 1462914 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5342. Min Act: -0.1700
Data Index: 3574769 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5655. Min Act: -0.1700
Data Index: 2870751 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19