Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1214 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0461. Min Range: -10.0461
Max Act: 10.0461. Min Act: -0.1700
Data Index: 1612107 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.9836. Min Act: -0.1700
Data Index: 1155805 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.9211. Min Act: -0.1700
Data Index: 8435558 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.7961. Min Act: -0.1700
Data Index: 2574838 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.7961. Min Act: -0.1700
Data Index: 8779207 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.7336. Min Act: -0.1700
Data Index: 8119571 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.6086. Min Act: -0.1700
Data Index: 1035105 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.5461. Min Act: -0.1700
Data Index: 722009 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.3586. Min Act: -0.1700
Data Index: 6123838 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.4211. Min Act: -0.1700
Data Index: 8131686 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.4211. Min Act: -0.1700
Data Index: 5438930 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.3586. Min Act: -0.1700
Data Index: 8120645 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.2961. Min Act: -0.1700
Data Index: 1670266 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.2336. Min Act: -0.1700
Data Index: 1873604 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.2336. Min Act: -0.1700
Data Index: 6413696 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.2336. Min Act: -0.1700
Data Index: 4310043 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.1711. Min Act: -0.1700
Data Index: 743755 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.1711. Min Act: -0.1700
Data Index: 186538 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.1711. Min Act: -0.1700
Data Index: 3114140 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0461. Min Range: -10.0461
Max Act: 9.1711. Min Act: -0.1700
Data Index: 5014052 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19