Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1461
Data Index: 6428231 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1608
Data Index: 4003153 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1699
Data Index: 2278381 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1486
Data Index: 1771859 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1692
Data Index: 6128439 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1680
Data Index: 3007903 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1688
Data Index: 735020 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1694
Data Index: 6427424 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1700
Data Index: 6038026 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1641
Data Index: 5752548 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1655
Data Index: 551033 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1684
Data Index: 5707940 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1695
Data Index: 5319330 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1634
Data Index: 344946 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1409
Data Index: 6868690 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1685
Data Index: 83968 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1608
Data Index: 6280643 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1461
Data Index: 6815006 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1662
Data Index: 839171 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2830. Min Range: -0.2830
Max Act: 0.2830. Min Act: -0.1566
Data Index: 1300641 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19