Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 47 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2293. Min Range: -8.2293
Max Act: 8.2293. Min Act: -0.1700
Data Index: 5194604 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2293. Min Range: -8.2293
Max Act: 8.0418. Min Act: -0.1700
Data Index: 7273825 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.8856. Min Act: -0.1700
Data Index: 8678400 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.8856. Min Act: -0.1700
Data Index: 1224761 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.8231. Min Act: -0.1700
Data Index: 7596451 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.7606. Min Act: -0.1700
Data Index: 3732750 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.7293. Min Act: -0.1700
Data Index: 7088091 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.7293. Min Act: -0.1700
Data Index: 5203204 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.6981. Min Act: -0.1700
Data Index: 8246293 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.6981. Min Act: -0.1700
Data Index: 1588931 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.6668. Min Act: -0.1700
Data Index: 1375658 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.5731. Min Act: -0.1700
Data Index: 3201291 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.5731. Min Act: -0.1700
Data Index: 1928801 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.5731. Min Act: -0.1700
Data Index: 7385875 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.5106. Min Act: -0.1700
Data Index: 5798618 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.4793. Min Act: -0.1700
Data Index: 3637454 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.5106. Min Act: -0.1700
Data Index: 4720380 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.5106. Min Act: -0.1700
Data Index: 7477884 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.5106. Min Act: -0.1700
Data Index: 4254913 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2293. Min Range: -8.2293
Max Act: 7.4793. Min Act: -0.1700
Data Index: 1801595 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19