Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3807 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3682. Min Range: -7.3682
Max Act: 7.3682. Min Act: -0.1700
Data Index: 6003198 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.9619. Min Act: -0.1700
Data Index: 610962 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.8057. Min Act: -0.1700
Data Index: 7673189 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.7744. Min Act: -0.1700
Data Index: 5151563 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.7432. Min Act: -0.1700
Data Index: 5698475 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.7432. Min Act: -0.1700
Data Index: 3553479 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.6807. Min Act: -0.1700
Data Index: 5325399 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.7119. Min Act: -0.1700
Data Index: 4430115 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.7119. Min Act: -0.1700
Data Index: 1391420 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.6807. Min Act: -0.1700
Data Index: 5597835 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.6807. Min Act: -0.1700
Data Index: 2732138 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.6494. Min Act: -0.1700
Data Index: 5774277 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.6182. Min Act: -0.1700
Data Index: 7402517 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.6182. Min Act: -0.1700
Data Index: 922969 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.6182. Min Act: -0.1700
Data Index: 5291136 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.5869. Min Act: -0.1700
Data Index: 7459521 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.5869. Min Act: -0.1700
Data Index: 3280542 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.5557. Min Act: -0.1700
Data Index: 7203212 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.6182. Min Act: -0.1700
Data Index: 3220092 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3682. Min Range: -7.3682
Max Act: 6.5869. Min Act: -0.1700
Data Index: 5938174 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19