Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 29 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1872. Min Range: -3.1872
Max Act: 3.1872. Min Act: -0.1698
Data Index: 2367701 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1872. Min Range: -3.1872
Max Act: 3.1558. Min Act: -0.1642
Data Index: 1358698 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1872. Min Range: -3.1872
Max Act: 3.1085. Min Act: -0.1583
Data Index: 6700953 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1872. Min Range: -3.1872
Max Act: 3.0454. Min Act: -0.1699
Data Index: 6220162 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1872. Min Range: -3.1872
Max Act: 3.0454. Min Act: -0.1700
Data Index: 2470042 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1872. Min Range: -3.1872
Max Act: 3.0138. Min Act: -0.1700
Data Index: 6107496 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1872. Min Range: -3.1872
Max Act: 2.9664. Min Act: -0.1481
Data Index: 7676167 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1872. Min Range: -3.1872
Max Act: 2.9980. Min Act: -0.1695
Data Index: 5457829 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1872. Min Range: -3.1872
Max Act: 2.9822. Min Act: -0.1689
Data Index: 5734239 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1872. Min Range: -3.1872
Max Act: 2.9664. Min Act: -0.1687
Data Index: 734209 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1872. Min Range: -3.1872
Max Act: 2.9822. Min Act: -0.1598
Data Index: 635789 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1872. Min Range: -3.1872
Max Act: 2.9664. Min Act: -0.1390
Data Index: 980990 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1872. Min Range: -3.1872
Max Act: 2.9664. Min Act: -0.1691
Data Index: 8528016 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1872. Min Range: -3.1872
Max Act: 2.9664. Min Act: -0.1657
Data Index: 6060928 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1872. Min Range: -3.1872
Max Act: 2.9189. Min Act: -0.1639
Data Index: 7756186 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1872. Min Range: -3.1872
Max Act: 2.9506. Min Act: -0.1692
Data Index: 515439 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1872. Min Range: -3.1872
Max Act: 2.9506. Min Act: -0.1698
Data Index: 4865069 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1872. Min Range: -3.1872
Max Act: 2.9506. Min Act: -0.1665
Data Index: 7979597 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1872. Min Range: -3.1872
Max Act: 2.9031. Min Act: -0.1698
Data Index: 3047345 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1872. Min Range: -3.1872
Max Act: 2.9506. Min Act: -0.1698
Data Index: 8282021 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19