Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3433 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1304. Min Range: -7.1304
Max Act: 7.1304. Min Act: -0.1700
Data Index: 8144437 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1304. Min Range: -7.1304
Max Act: 6.4429. Min Act: -0.1700
Data Index: 4319244 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1304. Min Range: -7.1304
Max Act: 6.3179. Min Act: -0.1700
Data Index: 4846160 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1304. Min Range: -7.1304
Max Act: 6.0054. Min Act: -0.1700
Data Index: 7803751 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1304. Min Range: -7.1304
Max Act: 6.0054. Min Act: -0.1700
Data Index: 6963824 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1304. Min Range: -7.1304
Max Act: 6.0054. Min Act: -0.1700
Data Index: 7089164 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1304. Min Range: -7.1304
Max Act: 5.9742. Min Act: -0.1700
Data Index: 7795194 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1304. Min Range: -7.1304
Max Act: 5.9742. Min Act: -0.1700
Data Index: 7145308 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1304. Min Range: -7.1304
Max Act: 6.0054. Min Act: -0.1700
Data Index: 5094154 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1304. Min Range: -7.1304
Max Act: 5.9742. Min Act: -0.1700
Data Index: 986600 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1304. Min Range: -7.1304
Max Act: 5.9429. Min Act: -0.1700
Data Index: 7283703 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1304. Min Range: -7.1304
Max Act: 5.9429. Min Act: -0.1700
Data Index: 8183155 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1304. Min Range: -7.1304
Max Act: 5.9742. Min Act: -0.1700
Data Index: 5197798 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1304. Min Range: -7.1304
Max Act: 5.9429. Min Act: -0.1700
Data Index: 110155 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1304. Min Range: -7.1304
Max Act: 5.9117. Min Act: -0.1700
Data Index: 4213517 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1304. Min Range: -7.1304
Max Act: 5.9429. Min Act: -0.1700
Data Index: 2415424 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1304. Min Range: -7.1304
Max Act: 5.9117. Min Act: -0.1700
Data Index: 6579586 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1304. Min Range: -7.1304
Max Act: 5.9117. Min Act: -0.1700
Data Index: 4766388 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1304. Min Range: -7.1304
Max Act: 5.8804. Min Act: -0.1700
Data Index: 2518266 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1304. Min Range: -7.1304
Max Act: 5.9117. Min Act: -0.1700
Data Index: 6362909 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19