Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 48 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0339. Min Range: -6.0339
Max Act: 6.0339. Min Act: -0.1700
Data Index: 451187 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0339. Min Range: -6.0339
Max Act: 6.0027. Min Act: -0.1700
Data Index: 975177 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.9714. Min Act: -0.1700
Data Index: 4933434 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.9714. Min Act: -0.1700
Data Index: 1518946 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.9089. Min Act: -0.1700
Data Index: 5019158 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.9089. Min Act: -0.1700
Data Index: 5136772 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.8777. Min Act: -0.1700
Data Index: 744163 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.8464. Min Act: -0.1700
Data Index: 7852534 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.8464. Min Act: -0.1700
Data Index: 3347339 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.7839. Min Act: -0.1700
Data Index: 1738181 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.7839. Min Act: -0.1700
Data Index: 1719390 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.7214. Min Act: -0.1700
Data Index: 6162814 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.6902. Min Act: -0.1700
Data Index: 7771880 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.6902. Min Act: -0.1700
Data Index: 7797414 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.6589. Min Act: -0.1700
Data Index: 4556396 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.5964. Min Act: -0.1700
Data Index: 2184689 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.6277. Min Act: -0.1700
Data Index: 4817582 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.5652. Min Act: -0.1700
Data Index: 4638541 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.6277. Min Act: -0.1700
Data Index: 1856928 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0339. Min Range: -6.0339
Max Act: 5.5964. Min Act: -0.1700
Data Index: 6001714 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19