Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 530 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.4156. Min Act: -0.1688
Data Index: 3080721 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.3716. Min Act: -0.1700
Data Index: 2119650 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.3628. Min Act: -0.1693
Data Index: 49265 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.3539. Min Act: -0.1684
Data Index: 2163511 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.3628. Min Act: -0.1674
Data Index: 3124331 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.3451. Min Act: -0.1699
Data Index: 473731 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.3187. Min Act: -0.1700
Data Index: 529322 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.3187. Min Act: -0.1700
Data Index: 5627134 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.3275. Min Act: -0.1700
Data Index: 2271749 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.3187. Min Act: -0.1700
Data Index: 8315928 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.3098. Min Act: -0.1700
Data Index: 5880232 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.3098. Min Act: -0.1691
Data Index: 6092131 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.3098. Min Act: -0.1698
Data Index: 5020998 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.2922. Min Act: -0.1682
Data Index: 2551068 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.2834. Min Act: -0.1698
Data Index: 1401277 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.3010. Min Act: -0.1700
Data Index: 8333813 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.2922. Min Act: -0.1700
Data Index: 7073521 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.2834. Min Act: -0.1700
Data Index: 2435043 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.2922. Min Act: -0.1700
Data Index: 2030562 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4156. Min Range: -1.4156
Max Act: 1.2834. Min Act: -0.1683
Data Index: 1727464 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19