Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.9449. Min Act: -0.1700
Data Index: 7046995 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.7887. Min Act: -0.1700
Data Index: 1780146 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.7262. Min Act: -0.1700
Data Index: 5399874 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.7262. Min Act: -0.1700
Data Index: 7634225 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.7574. Min Act: -0.1700
Data Index: 3607290 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.6637. Min Act: -0.1700
Data Index: 6374300 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.6324. Min Act: -0.1700
Data Index: 1424693 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.5387. Min Act: -0.1700
Data Index: 259717 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.5387. Min Act: -0.1700
Data Index: 6514069 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.4762. Min Act: -0.1700
Data Index: 1159754 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.5074. Min Act: -0.1700
Data Index: 4454608 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.5074. Min Act: -0.1700
Data Index: 6053517 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.4762. Min Act: -0.1700
Data Index: 1718555 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.4762. Min Act: -0.1700
Data Index: 8611931 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.4762. Min Act: -0.1700
Data Index: 7854399 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.4449. Min Act: -0.1700
Data Index: 381024 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.4449. Min Act: -0.1700
Data Index: 5849711 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.4137. Min Act: -0.1700
Data Index: 8529989 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.3512. Min Act: -0.1700
Data Index: 7113176 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9449. Min Range: -5.9449
Max Act: 5.3512. Min Act: -0.1700
Data Index: 7170195 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19