Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 317 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 7.5116. Min Range: -7.5116
Max Act: 7.5116. Min Act: -0.1700
Data Index: 6250325 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5116. Min Range: -7.5116
Max Act: 7.4491. Min Act: -0.1700
Data Index: 1847111 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.8866. Min Act: -0.1700
Data Index: 224709 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.7929. Min Act: -0.1700
Data Index: 5807091 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.6991. Min Act: -0.1700
Data Index: 2602901 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.6991. Min Act: -0.1700
Data Index: 7482697 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.6679. Min Act: -0.1700
Data Index: 6318146 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.5741. Min Act: -0.1700
Data Index: 4547979 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.6366. Min Act: -0.1700
Data Index: 5316434 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.6366. Min Act: -0.1700
Data Index: 2833248 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.6054. Min Act: -0.1700
Data Index: 8055654 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.5741. Min Act: -0.1700
Data Index: 6244962 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.5429. Min Act: -0.1700
Data Index: 5259123 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.5741. Min Act: -0.1700
Data Index: 8152152 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.5116. Min Act: -0.1700
Data Index: 8237598 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.5116. Min Act: -0.1700
Data Index: 7802924 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.5116. Min Act: -0.1700
Data Index: 7614642 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.4804. Min Act: -0.1700
Data Index: 1244074 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.4804. Min Act: -0.1700
Data Index: 6430645 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5116. Min Range: -7.5116
Max Act: 6.4804. Min Act: -0.1700
Data Index: 5760409 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19