Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3527 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3920. Min Range: -7.3920
Max Act: 7.3920. Min Act: -0.1700
Data Index: 7776097 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3920. Min Range: -7.3920
Max Act: 7.3295. Min Act: -0.1700
Data Index: 3257175 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3920. Min Range: -7.3920
Max Act: 7.2045. Min Act: -0.1700
Data Index: 4749528 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3920. Min Range: -7.3920
Max Act: 7.2045. Min Act: -0.1700
Data Index: 7000604 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3920. Min Range: -7.3920
Max Act: 6.9232. Min Act: -0.1700
Data Index: 1601615 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3920. Min Range: -7.3920
Max Act: 6.8295. Min Act: -0.1700
Data Index: 8055104 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3920. Min Range: -7.3920
Max Act: 6.7357. Min Act: -0.1700
Data Index: 2714305 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3920. Min Range: -7.3920
Max Act: 6.7045. Min Act: -0.1700
Data Index: 3822827 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3920. Min Range: -7.3920
Max Act: 6.6732. Min Act: -0.1700
Data Index: 8285516 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3920. Min Range: -7.3920
Max Act: 6.6732. Min Act: -0.1700
Data Index: 5778564 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3920. Min Range: -7.3920
Max Act: 6.6420. Min Act: -0.1700
Data Index: 3544575 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3920. Min Range: -7.3920
Max Act: 6.6420. Min Act: -0.1700
Data Index: 6180169 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3920. Min Range: -7.3920
Max Act: 6.6107. Min Act: -0.1700
Data Index: 3899303 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3920. Min Range: -7.3920
Max Act: 6.5795. Min Act: -0.1700
Data Index: 3004723 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3920. Min Range: -7.3920
Max Act: 6.5795. Min Act: -0.1700
Data Index: 6446952 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3920. Min Range: -7.3920
Max Act: 6.5482. Min Act: -0.1700
Data Index: 5820401 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3920. Min Range: -7.3920
Max Act: 6.5170. Min Act: -0.1700
Data Index: 7078091 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3920. Min Range: -7.3920
Max Act: 6.5170. Min Act: -0.1700
Data Index: 2988223 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3920. Min Range: -7.3920
Max Act: 6.4857. Min Act: -0.1700
Data Index: 1815173 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3920. Min Range: -7.3920
Max Act: 6.4857. Min Act: -0.1700
Data Index: 1262670 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19