Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.8554. Min Act: -0.1700
Data Index: 2230380 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.5742. Min Act: -0.1700
Data Index: 6225011 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.5429. Min Act: -0.1700
Data Index: 4659697 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.5429. Min Act: -0.1700
Data Index: 5321472 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.5117. Min Act: -0.1700
Data Index: 5223942 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.4804. Min Act: -0.1700
Data Index: 6677989 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.4804. Min Act: -0.1700
Data Index: 6859713 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.4492. Min Act: -0.1700
Data Index: 5578947 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.3867. Min Act: -0.1700
Data Index: 4214423 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.3554. Min Act: -0.1700
Data Index: 2581404 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.3867. Min Act: -0.1700
Data Index: 7618984 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.3867. Min Act: -0.1700
Data Index: 6236562 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.3554. Min Act: -0.1700
Data Index: 5276623 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.3242. Min Act: -0.1700
Data Index: 610147 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.2617. Min Act: -0.1700
Data Index: 8645011 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.2304. Min Act: -0.1700
Data Index: 98628 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.1992. Min Act: -0.1700
Data Index: 3335422 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.2304. Min Act: -0.1700
Data Index: 3426081 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.2304. Min Act: -0.1700
Data Index: 1553360 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8554. Min Range: -5.8554
Max Act: 5.2304. Min Act: -0.1700
Data Index: 144030 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19