Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4708 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1412. Min Range: -5.1412
Max Act: 5.1412. Min Act: -0.1700
Data Index: 7154039 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1412. Min Range: -5.1412
Max Act: 5.0475. Min Act: -0.1700
Data Index: 6492644 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1412. Min Range: -5.1412
Max Act: 5.0162. Min Act: -0.1700
Data Index: 4003992 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1412. Min Range: -5.1412
Max Act: 4.9537. Min Act: -0.1700
Data Index: 3575491 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1412. Min Range: -5.1412
Max Act: 4.9225. Min Act: -0.1700
Data Index: 4312304 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1412. Min Range: -5.1412
Max Act: 4.8912. Min Act: -0.1700
Data Index: 3853896 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1412. Min Range: -5.1412
Max Act: 4.8600. Min Act: -0.1700
Data Index: 4401992 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1412. Min Range: -5.1412
Max Act: 4.8287. Min Act: -0.1700
Data Index: 6115428 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1412. Min Range: -5.1412
Max Act: 4.8600. Min Act: -0.1700
Data Index: 3615456 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1412. Min Range: -5.1412
Max Act: 4.8600. Min Act: -0.1700
Data Index: 2882772 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1412. Min Range: -5.1412
Max Act: 4.8287. Min Act: -0.1700
Data Index: 5880971 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1412. Min Range: -5.1412
Max Act: 4.7975. Min Act: -0.1700
Data Index: 3254257 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1412. Min Range: -5.1412
Max Act: 4.7975. Min Act: -0.1700
Data Index: 199283 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1412. Min Range: -5.1412
Max Act: 4.7975. Min Act: -0.1700
Data Index: 8568117 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1412. Min Range: -5.1412
Max Act: 4.7350. Min Act: -0.1700
Data Index: 3705004 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1412. Min Range: -5.1412
Max Act: 4.7662. Min Act: -0.1700
Data Index: 7074987 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1412. Min Range: -5.1412
Max Act: 4.7662. Min Act: -0.1700
Data Index: 2444155 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1412. Min Range: -5.1412
Max Act: 4.7975. Min Act: -0.1700
Data Index: 5214469 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1412. Min Range: -5.1412
Max Act: 4.7662. Min Act: -0.1700
Data Index: 3048366 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1412. Min Range: -5.1412
Max Act: 4.7662. Min Act: -0.1700
Data Index: 6482826 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19