Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5686 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0299. Min Range: -5.0299
Max Act: 5.0299. Min Act: -0.1700
Data Index: 3999798 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.9674. Min Act: -0.1700
Data Index: 5512263 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.8111. Min Act: -0.1700
Data Index: 7096088 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.8111. Min Act: -0.1700
Data Index: 2539439 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.8111. Min Act: -0.1700
Data Index: 2625974 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7799. Min Act: -0.1700
Data Index: 8383512 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7486. Min Act: -0.1700
Data Index: 8450139 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7486. Min Act: -0.1700
Data Index: 8469340 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7486. Min Act: -0.1700
Data Index: 2001049 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7486. Min Act: -0.1700
Data Index: 1254767 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7486. Min Act: -0.1700
Data Index: 8607768 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7174. Min Act: -0.1700
Data Index: 2836954 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.6861. Min Act: -0.1700
Data Index: 8730191 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7174. Min Act: -0.1700
Data Index: 8241522 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.6861. Min Act: -0.1700
Data Index: 607508 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.6861. Min Act: -0.1700
Data Index: 3998470 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.6861. Min Act: -0.1700
Data Index: 411346 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.6861. Min Act: -0.1700
Data Index: 7914603 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.6861. Min Act: -0.1700
Data Index: 3449011 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.6861. Min Act: -0.1700
Data Index: 4435679 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19