Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4673 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2641. Min Range: -3.2641
Max Act: 3.2641. Min Act: -0.1700
Data Index: 5263181 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2641. Min Range: -3.2641
Max Act: 3.1855. Min Act: -0.1700
Data Index: 1308264 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2641. Min Range: -3.2641
Max Act: 3.1697. Min Act: -0.1700
Data Index: 2180784 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2641. Min Range: -3.2641
Max Act: 3.1383. Min Act: -0.1700
Data Index: 3027727 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2641. Min Range: -3.2641
Max Act: 3.1068. Min Act: -0.1700
Data Index: 2226252 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2641. Min Range: -3.2641
Max Act: 3.0752. Min Act: -0.1700
Data Index: 5263182 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2641. Min Range: -3.2641
Max Act: 3.0595. Min Act: -0.1700
Data Index: 3245631 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2641. Min Range: -3.2641
Max Act: 3.0752. Min Act: -0.1700
Data Index: 8033434 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2641. Min Range: -3.2641
Max Act: 3.0279. Min Act: -0.1700
Data Index: 3899815 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2641. Min Range: -3.2641
Max Act: 3.0437. Min Act: -0.1700
Data Index: 6711153 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2641. Min Range: -3.2641
Max Act: 3.0279. Min Act: -0.1700
Data Index: 2306224 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2641. Min Range: -3.2641
Max Act: 3.0279. Min Act: -0.1700
Data Index: 2008546 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2641. Min Range: -3.2641
Max Act: 3.0279. Min Act: -0.1700
Data Index: 5419898 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2641. Min Range: -3.2641
Max Act: 3.0279. Min Act: -0.1700
Data Index: 2187371 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2641. Min Range: -3.2641
Max Act: 3.0121. Min Act: -0.1700
Data Index: 8033433 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2641. Min Range: -3.2641
Max Act: 3.0121. Min Act: -0.1700
Data Index: 6866066 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2641. Min Range: -3.2641
Max Act: 2.9963. Min Act: -0.1700
Data Index: 6306889 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2641. Min Range: -3.2641
Max Act: 2.9963. Min Act: -0.1700
Data Index: 6464398 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2641. Min Range: -3.2641
Max Act: 2.9963. Min Act: -0.1700
Data Index: 6923261 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2641. Min Range: -3.2641
Max Act: 2.9805. Min Act: -0.1700
Data Index: 1912902 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19