Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1644 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.6377. Min Act: -0.1700
Data Index: 1678113 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.5439. Min Act: -0.1700
Data Index: 7419379 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.5439. Min Act: -0.1700
Data Index: 2867187 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.5439. Min Act: -0.1700
Data Index: 5842321 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.3252. Min Act: -0.1700
Data Index: 5408933 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.3252. Min Act: -0.1700
Data Index: 4129924 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.3564. Min Act: -0.1700
Data Index: 4954999 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.2939. Min Act: -0.1700
Data Index: 2670303 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.2627. Min Act: -0.1700
Data Index: 3128342 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.2627. Min Act: -0.1700
Data Index: 397609 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.2314. Min Act: -0.1700
Data Index: 3688806 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.2314. Min Act: -0.1700
Data Index: 4163869 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.2314. Min Act: -0.1700
Data Index: 6773985 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.2314. Min Act: -0.1700
Data Index: 5965377 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.2002. Min Act: -0.1700
Data Index: 6602240 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.2002. Min Act: -0.1700
Data Index: 3584148 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.1689. Min Act: -0.1700
Data Index: 466013 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.1689. Min Act: -0.1700
Data Index: 1568699 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.1689. Min Act: -0.1700
Data Index: 1188411 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6377. Min Range: -5.6377
Max Act: 5.2002. Min Act: -0.1700
Data Index: 6676492 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19