Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.6671. Min Act: -0.1700
Data Index: 1284685 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.5733. Min Act: -0.1700
Data Index: 1284682 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.5108. Min Act: -0.1700
Data Index: 1284683 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.4483. Min Act: -0.1700
Data Index: 1284686 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.3546. Min Act: -0.1700
Data Index: 6717524 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.3546. Min Act: -0.1700
Data Index: 4792550 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.2921. Min Act: -0.1700
Data Index: 350110 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.2608. Min Act: -0.1700
Data Index: 113281 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.2296. Min Act: -0.1700
Data Index: 3824188 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.2296. Min Act: -0.1700
Data Index: 8437273 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.1983. Min Act: -0.1700
Data Index: 970768 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.1983. Min Act: -0.1700
Data Index: 5643088 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.1983. Min Act: -0.1700
Data Index: 657970 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.1983. Min Act: -0.1700
Data Index: 7876927 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.1671. Min Act: -0.1700
Data Index: 6534787 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.1358. Min Act: -0.1700
Data Index: 274917 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.1671. Min Act: -0.1700
Data Index: 7908379 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.1358. Min Act: -0.1700
Data Index: 4903316 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.1358. Min Act: -0.1700
Data Index: 6092760 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6671. Min Range: -5.6671
Max Act: 5.1046. Min Act: -0.1700
Data Index: 3303241 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19