Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4433 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0655. Min Range: -5.0655
Max Act: 5.0655. Min Act: -0.1700
Data Index: 6045612 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0655. Min Range: -5.0655
Max Act: 5.0030. Min Act: -0.1700
Data Index: 7833294 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0655. Min Range: -5.0655
Max Act: 5.0030. Min Act: -0.1700
Data Index: 3686823 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0655. Min Range: -5.0655
Max Act: 4.9092. Min Act: -0.1700
Data Index: 1303669 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0655. Min Range: -5.0655
Max Act: 4.9405. Min Act: -0.1700
Data Index: 2591920 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0655. Min Range: -5.0655
Max Act: 4.8467. Min Act: -0.1700
Data Index: 2241546 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0655. Min Range: -5.0655
Max Act: 4.8467. Min Act: -0.1700
Data Index: 2369895 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0655. Min Range: -5.0655
Max Act: 4.8467. Min Act: -0.1700
Data Index: 6499129 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0655. Min Range: -5.0655
Max Act: 4.8155. Min Act: -0.1700
Data Index: 5395865 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0655. Min Range: -5.0655
Max Act: 4.8467. Min Act: -0.1700
Data Index: 3678983 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0655. Min Range: -5.0655
Max Act: 4.8467. Min Act: -0.1700
Data Index: 8465577 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0655. Min Range: -5.0655
Max Act: 4.8467. Min Act: -0.1700
Data Index: 749380 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0655. Min Range: -5.0655
Max Act: 4.8155. Min Act: -0.1700
Data Index: 882404 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0655. Min Range: -5.0655
Max Act: 4.7530. Min Act: -0.1700
Data Index: 7248535 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0655. Min Range: -5.0655
Max Act: 4.7842. Min Act: -0.1700
Data Index: 4250596 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0655. Min Range: -5.0655
Max Act: 4.7842. Min Act: -0.1700
Data Index: 8190612 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0655. Min Range: -5.0655
Max Act: 4.7842. Min Act: -0.1700
Data Index: 6745414 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0655. Min Range: -5.0655
Max Act: 4.7530. Min Act: -0.1700
Data Index: 4948395 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0655. Min Range: -5.0655
Max Act: 4.7842. Min Act: -0.1700
Data Index: 2885449 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0655. Min Range: -5.0655
Max Act: 4.7530. Min Act: -0.1700
Data Index: 329903 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19