Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3124 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.9372. Min Act: -0.1700
Data Index: 8755511 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.8747. Min Act: -0.1700
Data Index: 4021256 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.8747. Min Act: -0.1700
Data Index: 6960568 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.5622. Min Act: -0.1700
Data Index: 3499708 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.5622. Min Act: -0.1700
Data Index: 3438713 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.4997. Min Act: -0.1700
Data Index: 2933182 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.4997. Min Act: -0.1700
Data Index: 6564269 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.4685. Min Act: -0.1700
Data Index: 522552 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.4060. Min Act: -0.1700
Data Index: 4353806 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.3435. Min Act: -0.1700
Data Index: 8246196 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.3122. Min Act: -0.1700
Data Index: 7192355 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.2810. Min Act: -0.1700
Data Index: 1530011 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.2497. Min Act: -0.1700
Data Index: 8123343 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.2185. Min Act: -0.1700
Data Index: 1409360 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.2497. Min Act: -0.1700
Data Index: 1872712 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.2185. Min Act: -0.1700
Data Index: 6448203 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.2497. Min Act: -0.1700
Data Index: 6928426 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.1872. Min Act: -0.1700
Data Index: 1995138 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.1872. Min Act: -0.1700
Data Index: 2896311 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9372. Min Range: -7.9372
Max Act: 7.1872. Min Act: -0.1700
Data Index: 6756613 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19