Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 137 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0982. Min Range: -8.0982
Max Act: 8.0982. Min Act: -0.1700
Data Index: 7867115 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.9419. Min Act: -0.1700
Data Index: 847731 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.9419. Min Act: -0.1700
Data Index: 3828283 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.9107. Min Act: -0.1700
Data Index: 3870615 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.8794. Min Act: -0.1700
Data Index: 6319318 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.7857. Min Act: -0.1700
Data Index: 350589 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.7857. Min Act: -0.1700
Data Index: 5829238 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.8169. Min Act: -0.1700
Data Index: 1232177 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.7857. Min Act: -0.1700
Data Index: 5856812 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.7232. Min Act: -0.1700
Data Index: 4685245 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.6919. Min Act: -0.1700
Data Index: 3870616 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.6294. Min Act: -0.1700
Data Index: 6163801 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.5669. Min Act: -0.1700
Data Index: 7867114 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.5357. Min Act: -0.1700
Data Index: 3828282 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.2544. Min Act: -0.1700
Data Index: 2296691 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.1607. Min Act: -0.1700
Data Index: 7301988 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.1294. Min Act: -0.1700
Data Index: 3605305 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.0982. Min Act: -0.1700
Data Index: 5061078 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.0357. Min Act: -0.1700
Data Index: 6202684 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0982. Min Range: -8.0982
Max Act: 7.0044. Min Act: -0.1700
Data Index: 3605295 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19