Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4750 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.6013. Min Act: -0.1700
Data Index: 1332660 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.5388. Min Act: -0.1700
Data Index: 552308 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.5388. Min Act: -0.1700
Data Index: 4594739 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.3513. Min Act: -0.1700
Data Index: 6651614 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.3825. Min Act: -0.1700
Data Index: 5409215 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.3513. Min Act: -0.1700
Data Index: 8664036 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.3513. Min Act: -0.1700
Data Index: 7958595 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.3513. Min Act: -0.1700
Data Index: 5156215 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.3513. Min Act: -0.1700
Data Index: 6452894 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.3200. Min Act: -0.1700
Data Index: 2803107 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.3513. Min Act: -0.1700
Data Index: 4107646 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.3513. Min Act: -0.1700
Data Index: 3096493 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.3200. Min Act: -0.1700
Data Index: 4653430 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.3200. Min Act: -0.1700
Data Index: 5889339 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.3513. Min Act: -0.1700
Data Index: 7780459 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.2888. Min Act: -0.1700
Data Index: 7896531 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.2575. Min Act: -0.1700
Data Index: 2964633 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.2575. Min Act: -0.1700
Data Index: 8550178 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.2263. Min Act: -0.1700
Data Index: 3411621 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6013. Min Range: -7.6013
Max Act: 7.2575. Min Act: -0.1700
Data Index: 7390953 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19