Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3050 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1928. Min Range: -3.1928
Max Act: 3.1770. Min Act: -0.1700
Data Index: 5293989 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1928. Min Range: -3.1928
Max Act: 3.1928. Min Act: -0.1700
Data Index: 2768883 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1928. Min Range: -3.1928
Max Act: 3.0983. Min Act: -0.1700
Data Index: 8321339 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1928. Min Range: -3.1928
Max Act: 3.0983. Min Act: -0.1700
Data Index: 7163221 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1928. Min Range: -3.1928
Max Act: 3.0826. Min Act: -0.1700
Data Index: 7502854 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1928. Min Range: -3.1928
Max Act: 3.0510. Min Act: -0.1700
Data Index: 6510807 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1928. Min Range: -3.1928
Max Act: 3.0510. Min Act: -0.1700
Data Index: 5293990 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1928. Min Range: -3.1928
Max Act: 3.0510. Min Act: -0.1700
Data Index: 6009281 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1928. Min Range: -3.1928
Max Act: 3.0194. Min Act: -0.1700
Data Index: 6156688 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1928. Min Range: -3.1928
Max Act: 3.0194. Min Act: -0.1700
Data Index: 8724091 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1928. Min Range: -3.1928
Max Act: 3.0036. Min Act: -0.1700
Data Index: 6003181 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1928. Min Range: -3.1928
Max Act: 3.0036. Min Act: -0.1700
Data Index: 7481575 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1928. Min Range: -3.1928
Max Act: 3.0036. Min Act: -0.1700
Data Index: 1940537 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1928. Min Range: -3.1928
Max Act: 2.9878. Min Act: -0.1700
Data Index: 932653 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1928. Min Range: -3.1928
Max Act: 2.9720. Min Act: -0.1700
Data Index: 2895897 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1928. Min Range: -3.1928
Max Act: 2.9720. Min Act: -0.1700
Data Index: 2931090 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1928. Min Range: -3.1928
Max Act: 2.9720. Min Act: -0.1700
Data Index: 3737571 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1928. Min Range: -3.1928
Max Act: 2.9878. Min Act: -0.1700
Data Index: 2238826 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1928. Min Range: -3.1928
Max Act: 2.9720. Min Act: -0.1700
Data Index: 2887376 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1928. Min Range: -3.1928
Max Act: 2.9720. Min Act: -0.1700
Data Index: 6716183 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19