Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3959 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.6028. Min Act: -0.1700
Data Index: 7185963 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.4153. Min Act: -0.1700
Data Index: 7597682 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.2278. Min Act: -0.1700
Data Index: 1669511 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.2278. Min Act: -0.1700
Data Index: 2463198 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.2278. Min Act: -0.1700
Data Index: 3538021 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.2278. Min Act: -0.1700
Data Index: 2623958 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.2278. Min Act: -0.1700
Data Index: 783018 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.2278. Min Act: -0.1700
Data Index: 1082594 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.2278. Min Act: -0.1700
Data Index: 1760899 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.2278. Min Act: -0.1700
Data Index: 3456661 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.2278. Min Act: -0.1700
Data Index: 4095171 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.2278. Min Act: -0.1700
Data Index: 3482681 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.2278. Min Act: -0.1700
Data Index: 510088 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.1653. Min Act: -0.1700
Data Index: 8585579 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.0715. Min Act: -0.1700
Data Index: 4773664 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.1028. Min Act: -0.1700
Data Index: 865263 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.1028. Min Act: -0.1700
Data Index: 6386714 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.0715. Min Act: -0.1700
Data Index: 7557178 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.0715. Min Act: -0.1700
Data Index: 2673393 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6028. Min Range: -5.6028
Max Act: 5.0090. Min Act: -0.1700
Data Index: 2874246 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19