Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 886 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.1928. Min Act: -0.1700
Data Index: 3439027 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.1303. Min Act: -0.1700
Data Index: 215241 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.1303. Min Act: -0.1700
Data Index: 1909304 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.1303. Min Act: -0.1700
Data Index: 308652 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.1303. Min Act: -0.1700
Data Index: 2362051 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.1303. Min Act: -0.1700
Data Index: 780439 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.0990. Min Act: -0.1700
Data Index: 2751318 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.1303. Min Act: -0.1700
Data Index: 4376693 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.0990. Min Act: -0.1700
Data Index: 6386889 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.0990. Min Act: -0.1700
Data Index: 6789177 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.0990. Min Act: -0.1700
Data Index: 7005458 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.0678. Min Act: -0.1700
Data Index: 5703794 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.0678. Min Act: -0.1700
Data Index: 2220712 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.0678. Min Act: -0.1700
Data Index: 5854787 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.0678. Min Act: -0.1700
Data Index: 937983 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.0365. Min Act: -0.1700
Data Index: 2950758 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.0365. Min Act: -0.1700
Data Index: 6610878 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.0365. Min Act: -0.1700
Data Index: 113587 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.0678. Min Act: -0.1700
Data Index: 1234726 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1928. Min Range: -5.1928
Max Act: 5.0365. Min Act: -0.1700
Data Index: 2016606 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19