Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5525 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0770. Min Range: -9.0770
Max Act: 9.0770. Min Act: -0.1700
Data Index: 4595175 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0770. Min Range: -9.0770
Max Act: 8.7020. Min Act: -0.1700
Data Index: 2624992 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0770. Min Range: -9.0770
Max Act: 8.7020. Min Act: -0.1700
Data Index: 5033928 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0770. Min Range: -9.0770
Max Act: 8.3895. Min Act: -0.1700
Data Index: 569862 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0770. Min Range: -9.0770
Max Act: 8.2645. Min Act: -0.1700
Data Index: 51085 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0770. Min Range: -9.0770
Max Act: 8.2020. Min Act: -0.1700
Data Index: 6459884 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0770. Min Range: -9.0770
Max Act: 8.1395. Min Act: -0.1700
Data Index: 4417797 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0770. Min Range: -9.0770
Max Act: 8.1395. Min Act: -0.1700
Data Index: 4911421 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0770. Min Range: -9.0770
Max Act: 8.1395. Min Act: -0.1700
Data Index: 6580088 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0770. Min Range: -9.0770
Max Act: 8.1395. Min Act: -0.1700
Data Index: 5705625 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0770. Min Range: -9.0770
Max Act: 8.1395. Min Act: -0.1700
Data Index: 5442534 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0770. Min Range: -9.0770
Max Act: 8.1395. Min Act: -0.1700
Data Index: 3833842 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0770. Min Range: -9.0770
Max Act: 8.0770. Min Act: -0.1700
Data Index: 282668 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0770. Min Range: -9.0770
Max Act: 8.0770. Min Act: -0.1700
Data Index: 5270574 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0770. Min Range: -9.0770
Max Act: 7.9520. Min Act: -0.1700
Data Index: 5909064 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0770. Min Range: -9.0770
Max Act: 8.0145. Min Act: -0.1700
Data Index: 370010 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0770. Min Range: -9.0770
Max Act: 8.0145. Min Act: -0.1700
Data Index: 756664 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0770. Min Range: -9.0770
Max Act: 7.9520. Min Act: -0.1700
Data Index: 864854 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0770. Min Range: -9.0770
Max Act: 7.8895. Min Act: -0.1700
Data Index: 3879635 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0770. Min Range: -9.0770
Max Act: 7.9520. Min Act: -0.1700
Data Index: 4946594 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19