Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1821 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.3864. Min Act: -0.1700
Data Index: 3229026 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.2922. Min Act: -0.1700
Data Index: 4103966 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1980. Min Act: -0.1700
Data Index: 2190034 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1665. Min Act: -0.1700
Data Index: 5559980 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1508. Min Act: -0.1700
Data Index: 8202048 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1350. Min Act: -0.1700
Data Index: 2776895 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.1193. Min Act: -0.1700
Data Index: 8213889 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.0720. Min Act: -0.1700
Data Index: 3790199 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.0720. Min Act: -0.1699
Data Index: 5785012 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.0877. Min Act: -0.1700
Data Index: 8059143 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.0877. Min Act: -0.1700
Data Index: 7405125 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.0562. Min Act: -0.1700
Data Index: 4519045 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.0562. Min Act: -0.1700
Data Index: 7334662 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.0404. Min Act: -0.1700
Data Index: 7399368 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.0720. Min Act: -0.1700
Data Index: 8139218 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.0246. Min Act: -0.1700
Data Index: 7735446 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.0562. Min Act: -0.1698
Data Index: 4469540 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.0088. Min Act: -0.1699
Data Index: 963764 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3864. Min Range: -3.3864
Max Act: 2.9930. Min Act: -0.1700
Data Index: 7410614 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3864. Min Range: -3.3864
Max Act: 3.0246. Min Act: -0.1700
Data Index: 2358732 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19