Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1759. Min Range: -6.1759
Max Act: 6.1759. Min Act: -0.1700
Data Index: 3450799 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1759. Min Range: -6.1759
Max Act: 6.0822. Min Act: -0.1700
Data Index: 4833583 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1759. Min Range: -6.1759
Max Act: 6.0197. Min Act: -0.1700
Data Index: 6488363 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.9259. Min Act: -0.1700
Data Index: 787178 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.8947. Min Act: -0.1700
Data Index: 4877364 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.9259. Min Act: -0.1700
Data Index: 6009333 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.8634. Min Act: -0.1700
Data Index: 6953728 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.8322. Min Act: -0.1700
Data Index: 2002935 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.8009. Min Act: -0.1700
Data Index: 5798379 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.8009. Min Act: -0.1700
Data Index: 7608604 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.8322. Min Act: -0.1700
Data Index: 2794268 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.8009. Min Act: -0.1700
Data Index: 3154031 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.7384. Min Act: -0.1700
Data Index: 4736773 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.7384. Min Act: -0.1700
Data Index: 2759931 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.7384. Min Act: -0.1700
Data Index: 8746082 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.7384. Min Act: -0.1700
Data Index: 3965675 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.7697. Min Act: -0.1700
Data Index: 4277265 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.7384. Min Act: -0.1700
Data Index: 7294328 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.7384. Min Act: -0.1700
Data Index: 5020798 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.7384. Min Act: -0.1700
Data Index: 1652000 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19