Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1453 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.6366. Min Act: -0.1700
Data Index: 7294070 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.5741. Min Act: -0.1700
Data Index: 6189196 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.2929. Min Act: -0.1700
Data Index: 3790687 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.2616. Min Act: -0.1700
Data Index: 8718547 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.2616. Min Act: -0.1700
Data Index: 5840895 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.2304. Min Act: -0.1700
Data Index: 3404457 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.1991. Min Act: -0.1700
Data Index: 5091625 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.1991. Min Act: -0.1700
Data Index: 5911995 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.1366. Min Act: -0.1700
Data Index: 5348871 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.1679. Min Act: -0.1700
Data Index: 3018441 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.1366. Min Act: -0.1700
Data Index: 6390198 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.1679. Min Act: -0.1700
Data Index: 810484 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.1366. Min Act: -0.1700
Data Index: 6368605 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.1054. Min Act: -0.1700
Data Index: 3228939 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.1054. Min Act: -0.1700
Data Index: 5276075 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.1366. Min Act: -0.1700
Data Index: 2744368 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.1054. Min Act: -0.1700
Data Index: 3500117 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.0741. Min Act: -0.1700
Data Index: 4089101 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.0429. Min Act: -0.1700
Data Index: 1114162 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6366. Min Range: -5.6366
Max Act: 5.0741. Min Act: -0.1700
Data Index: 7341601 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19