Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4481 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1624. Min Range: -6.1624
Max Act: 6.1624. Min Act: -0.1700
Data Index: 5593647 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1624. Min Range: -6.1624
Max Act: 6.1624. Min Act: -0.1700
Data Index: 8208643 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1624. Min Range: -6.1624
Max Act: 6.1624. Min Act: -0.1700
Data Index: 3862785 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1624. Min Range: -6.1624
Max Act: 6.1312. Min Act: -0.1700
Data Index: 3372091 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1624. Min Range: -6.1624
Max Act: 6.0999. Min Act: -0.1700
Data Index: 8115568 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1624. Min Range: -6.1624
Max Act: 6.0062. Min Act: -0.1700
Data Index: 514425 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.9749. Min Act: -0.1700
Data Index: 7780132 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.9749. Min Act: -0.1700
Data Index: 5914849 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.9749. Min Act: -0.1700
Data Index: 7015621 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.9749. Min Act: -0.1700
Data Index: 6715063 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.9437. Min Act: -0.1700
Data Index: 2767282 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.9437. Min Act: -0.1700
Data Index: 7338988 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.9124. Min Act: -0.1700
Data Index: 1453174 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.9124. Min Act: -0.1700
Data Index: 758844 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.9124. Min Act: -0.1700
Data Index: 4626613 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.9124. Min Act: -0.1700
Data Index: 3310883 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.9124. Min Act: -0.1700
Data Index: 7926405 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.8812. Min Act: -0.1700
Data Index: 7389489 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.8812. Min Act: -0.1700
Data Index: 5164571 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1624. Min Range: -6.1624
Max Act: 5.8499. Min Act: -0.1700
Data Index: 7563463 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19