Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4862 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.7211. Min Act: -0.1700
Data Index: 1099321 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.6586. Min Act: -0.1700
Data Index: 4639757 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.6274. Min Act: -0.1700
Data Index: 1078410 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.6274. Min Act: -0.1700
Data Index: 8183965 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.5024. Min Act: -0.1700
Data Index: 5812078 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.4711. Min Act: -0.1700
Data Index: 2228114 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.4711. Min Act: -0.1700
Data Index: 5006798 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.4711. Min Act: -0.1700
Data Index: 940339 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.4399. Min Act: -0.1700
Data Index: 2369969 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.4399. Min Act: -0.1700
Data Index: 811576 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.4086. Min Act: -0.1700
Data Index: 186676 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.3774. Min Act: -0.1700
Data Index: 455618 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.3774. Min Act: -0.1700
Data Index: 8193035 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.3774. Min Act: -0.1700
Data Index: 5720046 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.3774. Min Act: -0.1700
Data Index: 7327904 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.3461. Min Act: -0.1700
Data Index: 8480692 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.3461. Min Act: -0.1700
Data Index: 5456335 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.3149. Min Act: -0.1700
Data Index: 1696787 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.3149. Min Act: -0.1700
Data Index: 5067290 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7211. Min Range: -4.7211
Max Act: 4.3149. Min Act: -0.1700
Data Index: 3906942 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19