Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4967 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1755. Min Range: -4.1755
Max Act: 4.1755. Min Act: -0.1700
Data Index: 2560856 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1755. Min Range: -4.1755
Max Act: 4.1443. Min Act: -0.1700
Data Index: 6856549 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1755. Min Range: -4.1755
Max Act: 4.0818. Min Act: -0.1700
Data Index: 5871099 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1755. Min Range: -4.1755
Max Act: 4.0193. Min Act: -0.1700
Data Index: 3530889 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1755. Min Range: -4.1755
Max Act: 4.0505. Min Act: -0.1700
Data Index: 2560854 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1755. Min Range: -4.1755
Max Act: 4.0193. Min Act: -0.1700
Data Index: 7906522 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1755. Min Range: -4.1755
Max Act: 3.9880. Min Act: -0.1700
Data Index: 7412077 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1755. Min Range: -4.1755
Max Act: 4.0193. Min Act: -0.1700
Data Index: 190059 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1755. Min Range: -4.1755
Max Act: 3.9880. Min Act: -0.1700
Data Index: 3103501 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1755. Min Range: -4.1755
Max Act: 3.9880. Min Act: -0.1700
Data Index: 333857 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1755. Min Range: -4.1755
Max Act: 3.9567. Min Act: -0.1700
Data Index: 643710 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1755. Min Range: -4.1755
Max Act: 3.8942. Min Act: -0.1700
Data Index: 990581 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1755. Min Range: -4.1755
Max Act: 3.9255. Min Act: -0.1700
Data Index: 4315686 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1755. Min Range: -4.1755
Max Act: 3.8942. Min Act: -0.1700
Data Index: 1179567 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1755. Min Range: -4.1755
Max Act: 3.8942. Min Act: -0.1700
Data Index: 3537247 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1755. Min Range: -4.1755
Max Act: 3.8942. Min Act: -0.1700
Data Index: 4751760 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1755. Min Range: -4.1755
Max Act: 3.8629. Min Act: -0.1700
Data Index: 5256967 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1755. Min Range: -4.1755
Max Act: 3.8629. Min Act: -0.1700
Data Index: 4311772 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1755. Min Range: -4.1755
Max Act: 3.8629. Min Act: -0.1700
Data Index: 3778013 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1755. Min Range: -4.1755
Max Act: 3.8629. Min Act: -0.1700
Data Index: 2434478 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19