Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.4771. Min Act: -0.1685
Data Index: 6629720 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.4846. Min Act: -0.1699
Data Index: 6080206 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.4189. Min Act: -0.1700
Data Index: 1940103 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.4189. Min Act: -0.1695
Data Index: 2015154 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.4117. Min Act: -0.1680
Data Index: 786488 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.4117. Min Act: -0.1691
Data Index: 3634656 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.4046. Min Act: -0.1696
Data Index: 522862 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.4046. Min Act: -0.1692
Data Index: 5597389 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.4046. Min Act: -0.1688
Data Index: 7442104 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.4117. Min Act: -0.1690
Data Index: 6856498 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.3976. Min Act: -0.1700
Data Index: 7278040 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.3835. Min Act: -0.1695
Data Index: 5805592 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.3976. Min Act: -0.1700
Data Index: 6654356 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.3835. Min Act: -0.1619
Data Index: 7746340 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.3835. Min Act: -0.1697
Data Index: 5737243 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.3628. Min Act: -0.1696
Data Index: 6371675 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.3766. Min Act: -0.1700
Data Index: 1590120 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.3766. Min Act: -0.1698
Data Index: 5062593 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.3766. Min Act: -0.1681
Data Index: 5620381 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4846. Min Range: -0.4846
Max Act: 0.3559. Min Act: -0.1700
Data Index: 1029707 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19