Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3226 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.9857. Min Act: -0.1700
Data Index: 8718096 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.9545. Min Act: -0.1700
Data Index: 4857083 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.9232. Min Act: -0.1700
Data Index: 2109724 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.8920. Min Act: -0.1700
Data Index: 1501028 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.8295. Min Act: -0.1700
Data Index: 8543703 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.8607. Min Act: -0.1700
Data Index: 891048 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.6732. Min Act: -0.1700
Data Index: 8533143 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.6732. Min Act: -0.1700
Data Index: 1746021 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.6420. Min Act: -0.1700
Data Index: 5857622 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.6420. Min Act: -0.1700
Data Index: 3777418 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.6107. Min Act: -0.1700
Data Index: 170971 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.5795. Min Act: -0.1700
Data Index: 1266711 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.6107. Min Act: -0.1700
Data Index: 3462558 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.6107. Min Act: -0.1700
Data Index: 5645342 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.6107. Min Act: -0.1700
Data Index: 7149971 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.5795. Min Act: -0.1700
Data Index: 987195 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.5795. Min Act: -0.1700
Data Index: 1669496 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.5795. Min Act: -0.1700
Data Index: 3612482 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.5795. Min Act: -0.1700
Data Index: 3404327 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9857. Min Range: -6.9857
Max Act: 6.5795. Min Act: -0.1700
Data Index: 6338250 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19