Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3733 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5042. Min Range: -6.5042
Max Act: 6.5042. Min Act: -0.1700
Data Index: 5165436 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5042. Min Range: -6.5042
Max Act: 6.4417. Min Act: -0.1700
Data Index: 2407610 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5042. Min Range: -6.5042
Max Act: 6.2542. Min Act: -0.1700
Data Index: 1401065 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5042. Min Range: -6.5042
Max Act: 6.0042. Min Act: -0.1700
Data Index: 922678 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5042. Min Range: -6.5042
Max Act: 5.9730. Min Act: -0.1700
Data Index: 2922463 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5042. Min Range: -6.5042
Max Act: 5.8480. Min Act: -0.1700
Data Index: 7565662 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5042. Min Range: -6.5042
Max Act: 5.8480. Min Act: -0.1700
Data Index: 953838 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5042. Min Range: -6.5042
Max Act: 5.7855. Min Act: -0.1700
Data Index: 6217418 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5042. Min Range: -6.5042
Max Act: 5.8480. Min Act: -0.1700
Data Index: 4360033 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5042. Min Range: -6.5042
Max Act: 5.8167. Min Act: -0.1700
Data Index: 3562679 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5042. Min Range: -6.5042
Max Act: 5.7542. Min Act: -0.1700
Data Index: 6802847 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5042. Min Range: -6.5042
Max Act: 5.7542. Min Act: -0.1700
Data Index: 6484409 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5042. Min Range: -6.5042
Max Act: 5.7855. Min Act: -0.1700
Data Index: 5137538 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5042. Min Range: -6.5042
Max Act: 5.8167. Min Act: -0.1700
Data Index: 376622 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5042. Min Range: -6.5042
Max Act: 5.7542. Min Act: -0.1700
Data Index: 8677083 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5042. Min Range: -6.5042
Max Act: 5.7230. Min Act: -0.1700
Data Index: 24657 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5042. Min Range: -6.5042
Max Act: 5.7230. Min Act: -0.1700
Data Index: 3263553 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5042. Min Range: -6.5042
Max Act: 5.6917. Min Act: -0.1700
Data Index: 6793919 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5042. Min Range: -6.5042
Max Act: 5.7542. Min Act: -0.1700
Data Index: 2391338 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5042. Min Range: -6.5042
Max Act: 5.7230. Min Act: -0.1700
Data Index: 5085744 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19