Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.5650. Min Act: -0.1700
Data Index: 7669943 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.4400. Min Act: -0.1700
Data Index: 3329076 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.3775. Min Act: -0.1700
Data Index: 6890136 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.2525. Min Act: -0.1700
Data Index: 2559032 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.2525. Min Act: -0.1700
Data Index: 1602697 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.3150. Min Act: -0.1700
Data Index: 4859660 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.1900. Min Act: -0.1700
Data Index: 4506103 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.2525. Min Act: -0.1700
Data Index: 7009339 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.1900. Min Act: -0.1700
Data Index: 7071260 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.1900. Min Act: -0.1700
Data Index: 3396620 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.1275. Min Act: -0.1700
Data Index: 1363623 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.1275. Min Act: -0.1700
Data Index: 7332344 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.0650. Min Act: -0.1700
Data Index: 3935194 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.0650. Min Act: -0.1700
Data Index: 7689738 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.0650. Min Act: -0.1700
Data Index: 7410002 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.0650. Min Act: -0.1700
Data Index: 4839922 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.0650. Min Act: -0.1700
Data Index: 3551490 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.0025. Min Act: -0.1700
Data Index: 7085756 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5650. Min Range: -9.5650
Max Act: 9.0650. Min Act: -0.1700
Data Index: 1084984 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5650. Min Range: -9.5650
Max Act: 8.9400. Min Act: -0.1700
Data Index: 7240299 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19