Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2518 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.7323. Min Act: -0.1700
Data Index: 5341297 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.7323. Min Act: -0.1700
Data Index: 326338 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.6698. Min Act: -0.1700
Data Index: 6947126 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.5448. Min Act: -0.1700
Data Index: 5395228 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.4823. Min Act: -0.1700
Data Index: 422275 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.4198. Min Act: -0.1700
Data Index: 693772 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.4198. Min Act: -0.1700
Data Index: 5576648 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.4823. Min Act: -0.1700
Data Index: 6448343 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.3573. Min Act: -0.1700
Data Index: 4951382 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.4198. Min Act: -0.1700
Data Index: 3329140 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.4198. Min Act: -0.1700
Data Index: 3091812 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.4198. Min Act: -0.1700
Data Index: 6943590 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.3573. Min Act: -0.1700
Data Index: 7025003 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.3573. Min Act: -0.1700
Data Index: 1762182 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.2948. Min Act: -0.1700
Data Index: 8750442 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.2948. Min Act: -0.1700
Data Index: 8384194 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.2948. Min Act: -0.1700
Data Index: 1702545 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.2011. Min Act: -0.1700
Data Index: 4087286 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.2011. Min Act: -0.1700
Data Index: 8490655 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7323. Min Range: -8.7323
Max Act: 8.1073. Min Act: -0.1700
Data Index: 5029188 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19