Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2789 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0219. Min Range: -6.0219
Max Act: 6.0219. Min Act: -0.1700
Data Index: 5023153 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.9281. Min Act: -0.1700
Data Index: 7792210 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.7719. Min Act: -0.1700
Data Index: 6493206 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.7094. Min Act: -0.1700
Data Index: 5240865 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.7406. Min Act: -0.1700
Data Index: 4272396 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.7406. Min Act: -0.1700
Data Index: 940029 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.7094. Min Act: -0.1700
Data Index: 6090221 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.7094. Min Act: -0.1700
Data Index: 5498604 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.6781. Min Act: -0.1700
Data Index: 1968103 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.6469. Min Act: -0.1700
Data Index: 514420 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.5531. Min Act: -0.1700
Data Index: 7044338 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.5219. Min Act: -0.1700
Data Index: 2558441 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.4906. Min Act: -0.1700
Data Index: 4227696 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.4906. Min Act: -0.1700
Data Index: 4378185 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.4906. Min Act: -0.1700
Data Index: 1570064 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.4906. Min Act: -0.1700
Data Index: 437077 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.4906. Min Act: -0.1700
Data Index: 1150899 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.4594. Min Act: -0.1700
Data Index: 6819593 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.4594. Min Act: -0.1700
Data Index: 6809171 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0219. Min Range: -6.0219
Max Act: 5.4594. Min Act: -0.1700
Data Index: 4339254 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19