Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3962 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5283. Min Range: -6.5283
Max Act: 6.5283. Min Act: -0.1700
Data Index: 7608660 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5283. Min Range: -6.5283
Max Act: 6.1845. Min Act: -0.1700
Data Index: 3846488 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5283. Min Range: -6.5283
Max Act: 6.1845. Min Act: -0.1700
Data Index: 840308 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5283. Min Range: -6.5283
Max Act: 6.0908. Min Act: -0.1700
Data Index: 894004 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5283. Min Range: -6.5283
Max Act: 6.1220. Min Act: -0.1700
Data Index: 1867750 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5283. Min Range: -6.5283
Max Act: 6.0595. Min Act: -0.1700
Data Index: 5916779 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5283. Min Range: -6.5283
Max Act: 6.0908. Min Act: -0.1700
Data Index: 5212188 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5283. Min Range: -6.5283
Max Act: 6.0595. Min Act: -0.1700
Data Index: 4933754 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5283. Min Range: -6.5283
Max Act: 6.0283. Min Act: -0.1700
Data Index: 265953 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5283. Min Range: -6.5283
Max Act: 6.0283. Min Act: -0.1700
Data Index: 1234664 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5283. Min Range: -6.5283
Max Act: 6.0283. Min Act: -0.1700
Data Index: 5355829 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5283. Min Range: -6.5283
Max Act: 5.9658. Min Act: -0.1700
Data Index: 8812417 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5283. Min Range: -6.5283
Max Act: 5.9658. Min Act: -0.1700
Data Index: 7498833 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5283. Min Range: -6.5283
Max Act: 5.9345. Min Act: -0.1700
Data Index: 4378219 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5283. Min Range: -6.5283
Max Act: 5.9345. Min Act: -0.1700
Data Index: 7606591 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5283. Min Range: -6.5283
Max Act: 5.8720. Min Act: -0.1700
Data Index: 6416926 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5283. Min Range: -6.5283
Max Act: 5.8095. Min Act: -0.1700
Data Index: 2719993 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5283. Min Range: -6.5283
Max Act: 5.8408. Min Act: -0.1700
Data Index: 7833807 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5283. Min Range: -6.5283
Max Act: 5.8408. Min Act: -0.1700
Data Index: 2474874 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5283. Min Range: -6.5283
Max Act: 5.8408. Min Act: -0.1700
Data Index: 7870239 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19