Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3429 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2375. Min Range: -7.2375
Max Act: 7.2375. Min Act: -0.1700
Data Index: 6125518 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2375. Min Range: -7.2375
Max Act: 7.2062. Min Act: -0.1700
Data Index: 992201 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2375. Min Range: -7.2375
Max Act: 7.1750. Min Act: -0.1700
Data Index: 2998491 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2375. Min Range: -7.2375
Max Act: 7.1750. Min Act: -0.1700
Data Index: 4239980 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2375. Min Range: -7.2375
Max Act: 7.1125. Min Act: -0.1700
Data Index: 664644 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2375. Min Range: -7.2375
Max Act: 7.1125. Min Act: -0.1700
Data Index: 8536008 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2375. Min Range: -7.2375
Max Act: 7.0812. Min Act: -0.1700
Data Index: 8041457 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2375. Min Range: -7.2375
Max Act: 7.1125. Min Act: -0.1700
Data Index: 6734884 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2375. Min Range: -7.2375
Max Act: 7.0812. Min Act: -0.1700
Data Index: 6409193 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2375. Min Range: -7.2375
Max Act: 7.0187. Min Act: -0.1700
Data Index: 6647187 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2375. Min Range: -7.2375
Max Act: 7.0187. Min Act: -0.1700
Data Index: 3837323 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2375. Min Range: -7.2375
Max Act: 6.9562. Min Act: -0.1700
Data Index: 1721816 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2375. Min Range: -7.2375
Max Act: 6.9250. Min Act: -0.1700
Data Index: 8675905 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2375. Min Range: -7.2375
Max Act: 6.9250. Min Act: -0.1700
Data Index: 3583413 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2375. Min Range: -7.2375
Max Act: 6.8312. Min Act: -0.1700
Data Index: 8390933 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2375. Min Range: -7.2375
Max Act: 6.8625. Min Act: -0.1700
Data Index: 1286952 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2375. Min Range: -7.2375
Max Act: 6.8312. Min Act: -0.1700
Data Index: 2835875 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2375. Min Range: -7.2375
Max Act: 6.8000. Min Act: -0.1700
Data Index: 1518651 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2375. Min Range: -7.2375
Max Act: 6.8000. Min Act: -0.1700
Data Index: 6721301 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2375. Min Range: -7.2375
Max Act: 6.7687. Min Act: -0.1700
Data Index: 3991879 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19