Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4707. Min Range: -6.4707
Max Act: 6.4707. Min Act: -0.1700
Data Index: 567925 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4707. Min Range: -6.4707
Max Act: 6.3145. Min Act: -0.1700
Data Index: 4829583 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4707. Min Range: -6.4707
Max Act: 6.3145. Min Act: -0.1700
Data Index: 1337848 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4707. Min Range: -6.4707
Max Act: 6.2832. Min Act: -0.1700
Data Index: 638533 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4707. Min Range: -6.4707
Max Act: 6.2207. Min Act: -0.1700
Data Index: 4553764 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4707. Min Range: -6.4707
Max Act: 6.2520. Min Act: -0.1700
Data Index: 6883328 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4707. Min Range: -6.4707
Max Act: 6.2520. Min Act: -0.1700
Data Index: 1002200 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4707. Min Range: -6.4707
Max Act: 6.1895. Min Act: -0.1700
Data Index: 8042819 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4707. Min Range: -6.4707
Max Act: 6.1582. Min Act: -0.1700
Data Index: 1339452 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4707. Min Range: -6.4707
Max Act: 6.0645. Min Act: -0.1700
Data Index: 8524242 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4707. Min Range: -6.4707
Max Act: 6.0957. Min Act: -0.1700
Data Index: 2774773 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4707. Min Range: -6.4707
Max Act: 6.0332. Min Act: -0.1700
Data Index: 6043657 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4707. Min Range: -6.4707
Max Act: 6.0020. Min Act: -0.1700
Data Index: 535644 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4707. Min Range: -6.4707
Max Act: 5.9395. Min Act: -0.1700
Data Index: 5618795 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4707. Min Range: -6.4707
Max Act: 5.9082. Min Act: -0.1700
Data Index: 423800 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4707. Min Range: -6.4707
Max Act: 5.8770. Min Act: -0.1700
Data Index: 7167902 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4707. Min Range: -6.4707
Max Act: 5.8770. Min Act: -0.1700
Data Index: 4723319 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4707. Min Range: -6.4707
Max Act: 5.9082. Min Act: -0.1700
Data Index: 7253783 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4707. Min Range: -6.4707
Max Act: 5.9082. Min Act: -0.1700
Data Index: 7500443 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4707. Min Range: -6.4707
Max Act: 5.8770. Min Act: -0.1700
Data Index: 5768201 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19