Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2531 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.4869. Min Act: -0.1700
Data Index: 2487214 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.4869. Min Act: -0.1700
Data Index: 3332926 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.4244. Min Act: -0.1699
Data Index: 5786065 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.4556. Min Act: -0.1700
Data Index: 8713489 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.3931. Min Act: -0.1700
Data Index: 554259 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.4244. Min Act: -0.1699
Data Index: 2788152 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.3931. Min Act: -0.1700
Data Index: 5939079 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.3306. Min Act: -0.1700
Data Index: 5927710 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.2681. Min Act: -0.1699
Data Index: 3278952 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.2369. Min Act: -0.1699
Data Index: 8102491 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.2056. Min Act: -0.1700
Data Index: 5906582 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.1744. Min Act: -0.1700
Data Index: 5608489 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.1119. Min Act: -0.1700
Data Index: 5592847 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.1431. Min Act: -0.1700
Data Index: 5534973 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.0494. Min Act: -0.1633
Data Index: 3485507 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.1119. Min Act: -0.1694
Data Index: 2393021 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.0806. Min Act: -0.1700
Data Index: 5738469 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.0494. Min Act: -0.1700
Data Index: 5200374 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.0494. Min Act: -0.1692
Data Index: 5120629 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4869. Min Range: -7.4869
Max Act: 7.0494. Min Act: -0.1700
Data Index: 5216118 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19