Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4086 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6233. Min Range: -7.6233
Max Act: 7.6233. Min Act: -0.1700
Data Index: 4586578 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6233. Min Range: -7.6233
Max Act: 7.2795. Min Act: -0.1700
Data Index: 4102369 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6233. Min Range: -7.6233
Max Act: 7.0608. Min Act: -0.1700
Data Index: 2585784 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6233. Min Range: -7.6233
Max Act: 7.0295. Min Act: -0.1700
Data Index: 8353124 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6233. Min Range: -7.6233
Max Act: 7.0295. Min Act: -0.1700
Data Index: 1285041 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6233. Min Range: -7.6233
Max Act: 6.9983. Min Act: -0.1700
Data Index: 3889611 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6233. Min Range: -7.6233
Max Act: 6.9983. Min Act: -0.1700
Data Index: 682689 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6233. Min Range: -7.6233
Max Act: 6.9670. Min Act: -0.1700
Data Index: 7131159 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6233. Min Range: -7.6233
Max Act: 6.9670. Min Act: -0.1700
Data Index: 2726862 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6233. Min Range: -7.6233
Max Act: 6.9670. Min Act: -0.1700
Data Index: 7490077 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6233. Min Range: -7.6233
Max Act: 6.9045. Min Act: -0.1700
Data Index: 3619852 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6233. Min Range: -7.6233
Max Act: 6.8733. Min Act: -0.1700
Data Index: 5699968 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6233. Min Range: -7.6233
Max Act: 6.8420. Min Act: -0.1700
Data Index: 6172147 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6233. Min Range: -7.6233
Max Act: 6.8108. Min Act: -0.1700
Data Index: 4469526 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6233. Min Range: -7.6233
Max Act: 6.7170. Min Act: -0.1700
Data Index: 7667954 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6233. Min Range: -7.6233
Max Act: 6.7795. Min Act: -0.1700
Data Index: 1661569 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6233. Min Range: -7.6233
Max Act: 6.7170. Min Act: -0.1700
Data Index: 912238 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6233. Min Range: -7.6233
Max Act: 6.7170. Min Act: -0.1700
Data Index: 496712 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6233. Min Range: -7.6233
Max Act: 6.6858. Min Act: -0.1700
Data Index: 4779337 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6233. Min Range: -7.6233
Max Act: 6.6858. Min Act: -0.1700
Data Index: 5698967 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19