Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.7694. Min Act: -0.1700
Data Index: 2075370 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.7694. Min Act: -0.1700
Data Index: 7919762 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.7262. Min Act: -0.1700
Data Index: 7384685 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.7175. Min Act: -0.1700
Data Index: 3474927 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.6915. Min Act: -0.1700
Data Index: 3474924 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.6742. Min Act: -0.1700
Data Index: 5759593 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.6742. Min Act: -0.1700
Data Index: 5759581 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.6568. Min Act: -0.1700
Data Index: 6493238 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.6655. Min Act: -0.1700
Data Index: 818429 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.6655. Min Act: -0.1574
Data Index: 6880478 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.6568. Min Act: -0.1700
Data Index: 7066045 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.6568. Min Act: -0.1700
Data Index: 1853385 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.6568. Min Act: -0.1700
Data Index: 4371846 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.6481. Min Act: -0.1700
Data Index: 8711403 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.6481. Min Act: -0.1700
Data Index: 4955837 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.6394. Min Act: -0.1700
Data Index: 2121227 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.6307. Min Act: -0.1700
Data Index: 4964474 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.6307. Min Act: -0.1700
Data Index: 1986978 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.6307. Min Act: -0.1700
Data Index: 3474922 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7694. Min Range: -1.7694
Max Act: 1.6307. Min Act: -0.1699
Data Index: 2255268 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19