Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3246 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1755. Min Range: -5.1755
Max Act: 5.1755. Min Act: -0.1700
Data Index: 5500014 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.9880. Min Act: -0.1700
Data Index: 4759995 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.9880. Min Act: -0.1700
Data Index: 6638662 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.9567. Min Act: -0.1700
Data Index: 4706949 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.9567. Min Act: -0.1700
Data Index: 7405252 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.9255. Min Act: -0.1700
Data Index: 1552646 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.8942. Min Act: -0.1700
Data Index: 31522 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.8942. Min Act: -0.1700
Data Index: 5174101 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.8630. Min Act: -0.1700
Data Index: 3851708 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.8942. Min Act: -0.1700
Data Index: 2166460 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.8630. Min Act: -0.1700
Data Index: 1318565 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.8630. Min Act: -0.1700
Data Index: 7031510 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.8630. Min Act: -0.1700
Data Index: 6089992 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.8630. Min Act: -0.1700
Data Index: 6672651 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.8317. Min Act: -0.1700
Data Index: 3989043 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.8317. Min Act: -0.1700
Data Index: 2497653 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.8317. Min Act: -0.1700
Data Index: 2399131 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.8317. Min Act: -0.1700
Data Index: 2899634 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.8317. Min Act: -0.1700
Data Index: 910347 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1755. Min Range: -5.1755
Max Act: 4.8317. Min Act: -0.1700
Data Index: 3237627 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19