Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2005 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2761. Min Range: -5.2761
Max Act: 5.2761. Min Act: -0.1700
Data Index: 7080019 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2761. Min Range: -5.2761
Max Act: 5.2136. Min Act: -0.1700
Data Index: 6801370 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2761. Min Range: -5.2761
Max Act: 5.0574. Min Act: -0.1700
Data Index: 2199842 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2761. Min Range: -5.2761
Max Act: 5.0261. Min Act: -0.1700
Data Index: 5997050 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2761. Min Range: -5.2761
Max Act: 5.0261. Min Act: -0.1700
Data Index: 4180916 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2761. Min Range: -5.2761
Max Act: 5.0261. Min Act: -0.1700
Data Index: 184009 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2761. Min Range: -5.2761
Max Act: 5.0261. Min Act: -0.1700
Data Index: 2412901 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2761. Min Range: -5.2761
Max Act: 5.0574. Min Act: -0.1700
Data Index: 6134439 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2761. Min Range: -5.2761
Max Act: 5.0261. Min Act: -0.1700
Data Index: 1040989 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2761. Min Range: -5.2761
Max Act: 4.9636. Min Act: -0.1700
Data Index: 906560 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2761. Min Range: -5.2761
Max Act: 4.9949. Min Act: -0.1700
Data Index: 3217663 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2761. Min Range: -5.2761
Max Act: 4.9636. Min Act: -0.1700
Data Index: 5926228 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2761. Min Range: -5.2761
Max Act: 4.9636. Min Act: -0.1700
Data Index: 4449722 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2761. Min Range: -5.2761
Max Act: 4.9324. Min Act: -0.1700
Data Index: 4372137 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2761. Min Range: -5.2761
Max Act: 4.9636. Min Act: -0.1700
Data Index: 8058234 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2761. Min Range: -5.2761
Max Act: 4.9636. Min Act: -0.1700
Data Index: 8382730 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2761. Min Range: -5.2761
Max Act: 4.9324. Min Act: -0.1700
Data Index: 4628940 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2761. Min Range: -5.2761
Max Act: 4.9324. Min Act: -0.1700
Data Index: 8574744 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2761. Min Range: -5.2761
Max Act: 4.9324. Min Act: -0.1700
Data Index: 4467187 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2761. Min Range: -5.2761
Max Act: 4.9011. Min Act: -0.1700
Data Index: 5838395 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19