Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 52 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.8872. Min Act: -0.1700
Data Index: 7264213 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.8714. Min Act: -0.1700
Data Index: 3577503 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.8872. Min Act: -0.1700
Data Index: 6337757 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.8714. Min Act: -0.1700
Data Index: 2780109 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.8555. Min Act: -0.1700
Data Index: 6877271 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.8555. Min Act: -0.1700
Data Index: 6120487 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.8555. Min Act: -0.1700
Data Index: 7971440 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.8396. Min Act: -0.1700
Data Index: 6120496 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.8237. Min Act: -0.1700
Data Index: 7531437 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.8237. Min Act: -0.1700
Data Index: 8523204 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.8078. Min Act: -0.1700
Data Index: 2780108 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.7918. Min Act: -0.1700
Data Index: 3445934 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.7600. Min Act: -0.1700
Data Index: 2782889 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.7759. Min Act: -0.1700
Data Index: 3445940 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.7759. Min Act: -0.1700
Data Index: 6120498 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.7759. Min Act: -0.1700
Data Index: 3445937 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.7600. Min Act: -0.1700
Data Index: 97707 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.7759. Min Act: -0.1700
Data Index: 7901623 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.7759. Min Act: -0.1700
Data Index: 953241 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8872. Min Range: -2.8872
Max Act: 2.7759. Min Act: -0.1700
Data Index: 1808159 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19