Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1115 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.9254. Min Act: -0.1700
Data Index: 6034754 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.9254. Min Act: -0.1700
Data Index: 7643820 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.9254. Min Act: -0.1700
Data Index: 280773 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.9083. Min Act: -0.1700
Data Index: 6907761 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.9254. Min Act: -0.1700
Data Index: 8599591 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.8913. Min Act: -0.1700
Data Index: 4580939 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.8913. Min Act: -0.1700
Data Index: 451192 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.8913. Min Act: -0.1700
Data Index: 8817823 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.8742. Min Act: -0.1700
Data Index: 4478588 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.8742. Min Act: -0.1700
Data Index: 1895574 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.8742. Min Act: -0.1700
Data Index: 1805680 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.8913. Min Act: -0.1700
Data Index: 1698087 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.8742. Min Act: -0.1700
Data Index: 8043696 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.8742. Min Act: -0.1700
Data Index: 4818004 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.8913. Min Act: -0.1700
Data Index: 2023971 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.8571. Min Act: -0.1700
Data Index: 3955040 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.8228. Min Act: -0.1700
Data Index: 4043308 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.8571. Min Act: -0.1700
Data Index: 1925369 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.8742. Min Act: -0.1700
Data Index: 1982385 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9254. Min Range: -1.9254
Max Act: 1.8571. Min Act: -0.1700
Data Index: 4304112 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19