Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3658 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.5770. Min Act: -0.1700
Data Index: 5451190 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.4833. Min Act: -0.1700
Data Index: 5843548 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.4208. Min Act: -0.1700
Data Index: 3316129 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.4208. Min Act: -0.1700
Data Index: 8429940 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.4208. Min Act: -0.1700
Data Index: 1400113 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.2958. Min Act: -0.1700
Data Index: 6979030 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.2645. Min Act: -0.1700
Data Index: 8373320 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.2333. Min Act: -0.1700
Data Index: 6701103 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.1395. Min Act: -0.1700
Data Index: 1453588 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.1395. Min Act: -0.1700
Data Index: 4242694 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.0770. Min Act: -0.1700
Data Index: 1485455 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.0770. Min Act: -0.1700
Data Index: 2169382 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5770. Min Range: -7.5770
Max Act: 7.0145. Min Act: -0.1700
Data Index: 52886 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5770. Min Range: -7.5770
Max Act: 6.9520. Min Act: -0.1700
Data Index: 172060 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5770. Min Range: -7.5770
Max Act: 6.9520. Min Act: -0.1700
Data Index: 8658419 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5770. Min Range: -7.5770
Max Act: 6.9520. Min Act: -0.1700
Data Index: 6807567 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5770. Min Range: -7.5770
Max Act: 6.8895. Min Act: -0.1700
Data Index: 2792439 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5770. Min Range: -7.5770
Max Act: 6.9520. Min Act: -0.1700
Data Index: 744603 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5770. Min Range: -7.5770
Max Act: 6.8895. Min Act: -0.1700
Data Index: 5630932 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5770. Min Range: -7.5770
Max Act: 6.8895. Min Act: -0.1700
Data Index: 3985681 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19