Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3151 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.4720. Min Act: -0.1700
Data Index: 3520824 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.4232. Min Act: -0.1700
Data Index: 466223 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3906. Min Act: -0.1700
Data Index: 5973892 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3906. Min Act: -0.1700
Data Index: 7397032 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3742. Min Act: -0.1700
Data Index: 4886521 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3579. Min Act: -0.1700
Data Index: 2175899 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3579. Min Act: -0.1700
Data Index: 8772275 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3579. Min Act: -0.1700
Data Index: 5888550 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3579. Min Act: -0.1700
Data Index: 757666 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3415. Min Act: -0.1700
Data Index: 8620537 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3251. Min Act: -0.1700
Data Index: 2781025 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3251. Min Act: -0.1700
Data Index: 7469145 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3415. Min Act: -0.1700
Data Index: 2730982 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3251. Min Act: -0.1700
Data Index: 1569582 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3086. Min Act: -0.1700
Data Index: 7187033 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3086. Min Act: -0.1700
Data Index: 6849393 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3251. Min Act: -0.1700
Data Index: 4345249 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3086. Min Act: -0.1700
Data Index: 3321788 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3251. Min Act: -0.1700
Data Index: 6528124 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4720. Min Range: -2.4720
Max Act: 2.3086. Min Act: -0.1700
Data Index: 6284095 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19