Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2412 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0491. Min Range: -4.0491
Max Act: 4.0491. Min Act: -0.1700
Data Index: 2214336 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.9553. Min Act: -0.1700
Data Index: 8806533 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.8928. Min Act: -0.1700
Data Index: 5309749 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.8928. Min Act: -0.1700
Data Index: 1048191 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.8615. Min Act: -0.1700
Data Index: 6673147 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.8615. Min Act: -0.1700
Data Index: 2107886 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.8615. Min Act: -0.1700
Data Index: 6888869 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.8302. Min Act: -0.1700
Data Index: 4913565 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.8615. Min Act: -0.1700
Data Index: 861311 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.8302. Min Act: -0.1700
Data Index: 848010 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.8615. Min Act: -0.1700
Data Index: 5242734 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.8302. Min Act: -0.1700
Data Index: 366463 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.8615. Min Act: -0.1700
Data Index: 2047223 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.7990. Min Act: -0.1700
Data Index: 3181771 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.8302. Min Act: -0.1700
Data Index: 2859437 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.8302. Min Act: -0.1700
Data Index: 2584613 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.8615. Min Act: -0.1700
Data Index: 2794990 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.8615. Min Act: -0.1700
Data Index: 5936872 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.8615. Min Act: -0.1700
Data Index: 7407941 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0491. Min Range: -4.0491
Max Act: 3.8302. Min Act: -0.1700
Data Index: 8055060 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19