Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 918 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.5034. Min Act: -0.1700
Data Index: 3596502 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.4407. Min Act: -0.1700
Data Index: 4675144 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.3624. Min Act: -0.1700
Data Index: 4112807 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.3624. Min Act: -0.1700
Data Index: 971434 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.3624. Min Act: -0.1700
Data Index: 6045198 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.2996. Min Act: -0.1700
Data Index: 2605442 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.2996. Min Act: -0.1700
Data Index: 154035 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.2839. Min Act: -0.1700
Data Index: 361667 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.2682. Min Act: -0.1700
Data Index: 3633094 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.2682. Min Act: -0.1700
Data Index: 7099902 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.2525. Min Act: -0.1700
Data Index: 7090896 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.2525. Min Act: -0.1700
Data Index: 7968125 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.2368. Min Act: -0.1700
Data Index: 6291552 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.2053. Min Act: -0.1700
Data Index: 778042 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.2210. Min Act: -0.1700
Data Index: 8415675 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.2053. Min Act: -0.1700
Data Index: 484476 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.2210. Min Act: -0.1700
Data Index: 8750224 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.2053. Min Act: -0.1700
Data Index: 531486 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.2053. Min Act: -0.1700
Data Index: 5942466 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5034. Min Range: -3.5034
Max Act: 3.2210. Min Act: -0.1700
Data Index: 2368217 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19