Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2642 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.5115. Min Act: -0.1693
Data Index: 4423211 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.4939. Min Act: -0.1700
Data Index: 581609 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.4851. Min Act: -0.1700
Data Index: 581610 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.4676. Min Act: -0.1700
Data Index: 4975778 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.4588. Min Act: -0.1700
Data Index: 6362357 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.4500. Min Act: -0.1700
Data Index: 707548 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.4412. Min Act: -0.1684
Data Index: 707546 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.4412. Min Act: -0.1689
Data Index: 707547 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.4412. Min Act: -0.1699
Data Index: 2908347 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.4412. Min Act: -0.1666
Data Index: 1208241 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.4324. Min Act: -0.1694
Data Index: 994427 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.4236. Min Act: -0.1693
Data Index: 6442297 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.4060. Min Act: -0.1693
Data Index: 2319502 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.4060. Min Act: -0.1700
Data Index: 5504262 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.4060. Min Act: -0.1700
Data Index: 22354 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.3971. Min Act: -0.1700
Data Index: 5918781 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.4060. Min Act: -0.1700
Data Index: 7355485 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.3971. Min Act: -0.1689
Data Index: 7641072 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.3883. Min Act: -0.1692
Data Index: 4075032 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5115. Min Range: -1.5115
Max Act: 1.3883. Min Act: -0.1700
Data Index: 6094972 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19