Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 817 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1340. Min Range: -7.1340
Max Act: 7.1340. Min Act: -0.1700
Data Index: 5381889 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1340. Min Range: -7.1340
Max Act: 7.1028. Min Act: -0.1700
Data Index: 1871104 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1340. Min Range: -7.1340
Max Act: 7.1028. Min Act: -0.1700
Data Index: 3716809 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1340. Min Range: -7.1340
Max Act: 7.0715. Min Act: -0.1700
Data Index: 2398884 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1340. Min Range: -7.1340
Max Act: 6.9465. Min Act: -0.1700
Data Index: 4606512 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1340. Min Range: -7.1340
Max Act: 6.8840. Min Act: -0.1700
Data Index: 8790877 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1340. Min Range: -7.1340
Max Act: 6.8215. Min Act: -0.1700
Data Index: 6256216 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1340. Min Range: -7.1340
Max Act: 6.8528. Min Act: -0.1700
Data Index: 5154807 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1340. Min Range: -7.1340
Max Act: 6.8215. Min Act: -0.1700
Data Index: 5747161 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1340. Min Range: -7.1340
Max Act: 6.8528. Min Act: -0.1700
Data Index: 310749 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1340. Min Range: -7.1340
Max Act: 6.8528. Min Act: -0.1700
Data Index: 2904749 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1340. Min Range: -7.1340
Max Act: 6.8528. Min Act: -0.1700
Data Index: 4307806 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1340. Min Range: -7.1340
Max Act: 6.8528. Min Act: -0.1700
Data Index: 7462838 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1340. Min Range: -7.1340
Max Act: 6.8840. Min Act: -0.1700
Data Index: 7595054 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1340. Min Range: -7.1340
Max Act: 6.8840. Min Act: -0.1700
Data Index: 1150013 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1340. Min Range: -7.1340
Max Act: 6.8528. Min Act: -0.1700
Data Index: 8569203 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1340. Min Range: -7.1340
Max Act: 6.8215. Min Act: -0.1700
Data Index: 5467302 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1340. Min Range: -7.1340
Max Act: 6.7903. Min Act: -0.1700
Data Index: 8346749 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1340. Min Range: -7.1340
Max Act: 6.8215. Min Act: -0.1700
Data Index: 5522282 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1340. Min Range: -7.1340
Max Act: 6.7903. Min Act: -0.1700
Data Index: 4505235 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19