Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1071 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0520. Min Range: -6.0520
Max Act: 6.0520. Min Act: -0.1700
Data Index: 5663946 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0520. Min Range: -6.0520
Max Act: 6.0520. Min Act: -0.1700
Data Index: 7852276 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.9582. Min Act: -0.1700
Data Index: 1550717 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.8645. Min Act: -0.1700
Data Index: 3903082 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.6457. Min Act: -0.1700
Data Index: 2180622 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.6145. Min Act: -0.1700
Data Index: 287340 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.5832. Min Act: -0.1700
Data Index: 4644480 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.5520. Min Act: -0.1700
Data Index: 4301060 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.5207. Min Act: -0.1699
Data Index: 8693908 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.4895. Min Act: -0.1700
Data Index: 2038414 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.4895. Min Act: -0.1700
Data Index: 1771482 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.4582. Min Act: -0.1700
Data Index: 1627015 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.4582. Min Act: -0.1700
Data Index: 2932607 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.4270. Min Act: -0.1700
Data Index: 3120711 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.4270. Min Act: -0.1700
Data Index: 6926720 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.4270. Min Act: -0.1700
Data Index: 3914157 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.3957. Min Act: -0.1700
Data Index: 4469010 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.3645. Min Act: -0.1700
Data Index: 4259086 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.3957. Min Act: -0.1700
Data Index: 5595384 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0520. Min Range: -6.0520
Max Act: 5.3957. Min Act: -0.1700
Data Index: 3903083 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19