Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 397 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.6494. Min Act: -0.1700
Data Index: 3169314 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.6175. Min Act: -0.1671
Data Index: 8287077 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.6175. Min Act: -0.1596
Data Index: 2975335 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.5782. Min Act: -0.1699
Data Index: 4182593 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.5550. Min Act: -0.1671
Data Index: 7911706 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.5550. Min Act: -0.1698
Data Index: 6280415 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.5550. Min Act: -0.1700
Data Index: 1108804 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.5396. Min Act: -0.1700
Data Index: 8696741 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.5319. Min Act: -0.1700
Data Index: 6616994 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.5243. Min Act: -0.1694
Data Index: 2837301 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.5243. Min Act: -0.1700
Data Index: 3958538 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.5167. Min Act: -0.1699
Data Index: 7249028 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.5092. Min Act: -0.1692
Data Index: 2412 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.5092. Min Act: -0.1699
Data Index: 7659219 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.5016. Min Act: -0.1700
Data Index: 3423515 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.4941. Min Act: -0.1700
Data Index: 559144 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.4941. Min Act: -0.1696
Data Index: 7768859 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.4941. Min Act: -0.1699
Data Index: 4904756 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.4867. Min Act: -0.1698
Data Index: 1856960 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6494. Min Range: -0.6494
Max Act: 0.4792. Min Act: -0.1700
Data Index: 3224151 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19