Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1547 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2770. Min Range: -6.2770
Max Act: 6.2770. Min Act: -0.1700
Data Index: 3937654 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2770. Min Range: -6.2770
Max Act: 6.1208. Min Act: -0.1700
Data Index: 6538809 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2770. Min Range: -6.2770
Max Act: 6.1520. Min Act: -0.1700
Data Index: 2996429 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2770. Min Range: -6.2770
Max Act: 6.0270. Min Act: -0.1700
Data Index: 5612870 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2770. Min Range: -6.2770
Max Act: 5.9958. Min Act: -0.1700
Data Index: 2983854 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2770. Min Range: -6.2770
Max Act: 5.9958. Min Act: -0.1700
Data Index: 8145085 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2770. Min Range: -6.2770
Max Act: 5.9958. Min Act: -0.1700
Data Index: 3957154 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2770. Min Range: -6.2770
Max Act: 5.9333. Min Act: -0.1700
Data Index: 3936377 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2770. Min Range: -6.2770
Max Act: 5.8708. Min Act: -0.1700
Data Index: 1847079 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2770. Min Range: -6.2770
Max Act: 5.8083. Min Act: -0.1700
Data Index: 606158 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2770. Min Range: -6.2770
Max Act: 5.8083. Min Act: -0.1700
Data Index: 626152 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2770. Min Range: -6.2770
Max Act: 5.7770. Min Act: -0.1700
Data Index: 7572145 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2770. Min Range: -6.2770
Max Act: 5.8083. Min Act: -0.1700
Data Index: 1351224 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2770. Min Range: -6.2770
Max Act: 5.6833. Min Act: -0.1700
Data Index: 4384278 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2770. Min Range: -6.2770
Max Act: 5.7458. Min Act: -0.1700
Data Index: 3197924 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2770. Min Range: -6.2770
Max Act: 5.7458. Min Act: -0.1700
Data Index: 3156224 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2770. Min Range: -6.2770
Max Act: 5.7145. Min Act: -0.1700
Data Index: 7238260 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2770. Min Range: -6.2770
Max Act: 5.7145. Min Act: -0.1700
Data Index: 4789838 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2770. Min Range: -6.2770
Max Act: 5.7145. Min Act: -0.1700
Data Index: 385914 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2770. Min Range: -6.2770
Max Act: 5.7145. Min Act: -0.1700
Data Index: 652678 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19