Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 736 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.7186. Min Act: -0.1700
Data Index: 5908602 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.4373. Min Act: -0.1700
Data Index: 1131033 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.3748. Min Act: -0.1700
Data Index: 4176904 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.3748. Min Act: -0.1700
Data Index: 5617653 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.3436. Min Act: -0.1700
Data Index: 1562669 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.2811. Min Act: -0.1700
Data Index: 498306 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.2186. Min Act: -0.1700
Data Index: 3392541 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.2186. Min Act: -0.1700
Data Index: 4208626 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.1873. Min Act: -0.1700
Data Index: 1566704 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.1561. Min Act: -0.1700
Data Index: 3206435 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.1561. Min Act: -0.1700
Data Index: 4188814 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.1873. Min Act: -0.1700
Data Index: 6403174 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.1561. Min Act: -0.1700
Data Index: 8242467 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.1248. Min Act: -0.1700
Data Index: 3233509 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.1248. Min Act: -0.1700
Data Index: 3117864 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.0936. Min Act: -0.1700
Data Index: 2539118 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.0936. Min Act: -0.1700
Data Index: 613083 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.0623. Min Act: -0.1700
Data Index: 2145692 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.0936. Min Act: -0.1700
Data Index: 417313 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7186. Min Range: -6.7186
Max Act: 6.0623. Min Act: -0.1700
Data Index: 5951155 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19