Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3031 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.6284. Min Act: -0.1700
Data Index: 4747190 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.6123. Min Act: -0.1700
Data Index: 4064571 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.6123. Min Act: -0.1700
Data Index: 2252146 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.5801. Min Act: -0.1700
Data Index: 8384100 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.5640. Min Act: -0.1700
Data Index: 3447828 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.5640. Min Act: -0.1700
Data Index: 3505711 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.5640. Min Act: -0.1700
Data Index: 6231044 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.5479. Min Act: -0.1700
Data Index: 4917537 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.5317. Min Act: -0.1700
Data Index: 3241716 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.5479. Min Act: -0.1700
Data Index: 3980391 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.5801. Min Act: -0.1700
Data Index: 8385564 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.5317. Min Act: -0.1700
Data Index: 4136776 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.5155. Min Act: -0.1700
Data Index: 5157988 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.5155. Min Act: -0.1700
Data Index: 3566593 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.4994. Min Act: -0.1700
Data Index: 7906395 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.4994. Min Act: -0.1700
Data Index: 8056581 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.4669. Min Act: -0.1700
Data Index: 6729557 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.4831. Min Act: -0.1700
Data Index: 1109944 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.4831. Min Act: -0.1700
Data Index: 6759850 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6284. Min Range: -2.6284
Max Act: 2.4831. Min Act: -0.1700
Data Index: 2252147 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19