Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4917 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.9492. Min Act: -0.1700
Data Index: 3492095 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.7305. Min Act: -0.1700
Data Index: 5117032 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.6055. Min Act: -0.1700
Data Index: 5280843 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.3867. Min Act: -0.1700
Data Index: 3003689 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.3242. Min Act: -0.1700
Data Index: 530500 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.2617. Min Act: -0.1700
Data Index: 5117031 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.2305. Min Act: -0.1700
Data Index: 5117028 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.2305. Min Act: -0.1700
Data Index: 4543751 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.2305. Min Act: -0.1700
Data Index: 777739 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.1992. Min Act: -0.1700
Data Index: 6146901 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.1992. Min Act: -0.1700
Data Index: 8375677 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.1992. Min Act: -0.1700
Data Index: 8634982 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.1992. Min Act: -0.1700
Data Index: 5094689 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.1680. Min Act: -0.1700
Data Index: 4681323 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.1680. Min Act: -0.1700
Data Index: 2137797 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.1367. Min Act: -0.1700
Data Index: 7344884 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.1367. Min Act: -0.1700
Data Index: 391960 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.1367. Min Act: -0.1700
Data Index: 505967 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.1367. Min Act: -0.1700
Data Index: 8454274 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.1367. Min Act: -0.1700
Data Index: 391961 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19