Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.6697. Min Act: -0.1700
Data Index: 1753111 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.6215. Min Act: -0.1700
Data Index: 4740712 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.5409. Min Act: -0.1700
Data Index: 8750804 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.5248. Min Act: -0.1700
Data Index: 8626858 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.4924. Min Act: -0.1700
Data Index: 6979593 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.4762. Min Act: -0.1700
Data Index: 2575774 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.4762. Min Act: -0.1700
Data Index: 8470875 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.4762. Min Act: -0.1700
Data Index: 4794862 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.4762. Min Act: -0.1700
Data Index: 8286933 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.4762. Min Act: -0.1700
Data Index: 1189543 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.4599. Min Act: -0.1700
Data Index: 4815046 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.4762. Min Act: -0.1700
Data Index: 3892367 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.4599. Min Act: -0.1700
Data Index: 7750562 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.4599. Min Act: -0.1700
Data Index: 7977369 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.4274. Min Act: -0.1700
Data Index: 361275 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.4437. Min Act: -0.1700
Data Index: 1189544 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.4437. Min Act: -0.1700
Data Index: 7840423 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.4437. Min Act: -0.1700
Data Index: 1853352 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.4437. Min Act: -0.1700
Data Index: 2218160 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6697. Min Range: -2.6697
Max Act: 2.4437. Min Act: -0.1700
Data Index: 2498034 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19