Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 82 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.7271. Min Act: -0.1700
Data Index: 5771513 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.6959. Min Act: -0.1700
Data Index: 1014738 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.6021. Min Act: -0.1700
Data Index: 7838131 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.6021. Min Act: -0.1700
Data Index: 8564476 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.5396. Min Act: -0.1700
Data Index: 2375847 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.5396. Min Act: -0.1700
Data Index: 2301993 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.4459. Min Act: -0.1700
Data Index: 8177527 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.4459. Min Act: -0.1700
Data Index: 8779176 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.4146. Min Act: -0.1700
Data Index: 8157324 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.4146. Min Act: -0.1700
Data Index: 2610452 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.3834. Min Act: -0.1700
Data Index: 1455756 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.3834. Min Act: -0.1700
Data Index: 7806231 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.3521. Min Act: -0.1700
Data Index: 5180879 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.3521. Min Act: -0.1700
Data Index: 128859 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.3521. Min Act: -0.1700
Data Index: 2375846 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.3209. Min Act: -0.1700
Data Index: 8336405 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.3209. Min Act: -0.1700
Data Index: 8588626 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.2896. Min Act: -0.1700
Data Index: 8107650 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.2584. Min Act: -0.1700
Data Index: 6976233 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7271. Min Range: -6.7271
Max Act: 6.2584. Min Act: -0.1700
Data Index: 5663070 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19