Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2852 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.2707. Min Act: -0.1700
Data Index: 1795332 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.2395. Min Act: -0.1700
Data Index: 6358490 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.2395. Min Act: -0.1700
Data Index: 5941809 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.2082. Min Act: -0.1700
Data Index: 2513463 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.2082. Min Act: -0.1700
Data Index: 1762108 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.1457. Min Act: -0.1700
Data Index: 8231309 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.1457. Min Act: -0.1700
Data Index: 5170866 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.1457. Min Act: -0.1700
Data Index: 4501019 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.1457. Min Act: -0.1700
Data Index: 4490935 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.1145. Min Act: -0.1700
Data Index: 8310680 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.0832. Min Act: -0.1700
Data Index: 2165321 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.0520. Min Act: -0.1700
Data Index: 6181952 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.0520. Min Act: -0.1700
Data Index: 8076348 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.0520. Min Act: -0.1700
Data Index: 8725386 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.0520. Min Act: -0.1700
Data Index: 3110098 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.0520. Min Act: -0.1700
Data Index: 5092355 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.0207. Min Act: -0.1700
Data Index: 6812030 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.0520. Min Act: -0.1700
Data Index: 8428797 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2707. Min Range: -6.2707
Max Act: 6.0207. Min Act: -0.1700
Data Index: 6010413 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2707. Min Range: -6.2707
Max Act: 5.9582. Min Act: -0.1700
Data Index: 7826150 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19