Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3394 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.1812. Min Act: -0.1700
Data Index: 934236 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.1654. Min Act: -0.1700
Data Index: 1319220 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.1182. Min Act: -0.1700
Data Index: 8423476 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.0867. Min Act: -0.1700
Data Index: 3705959 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.1024. Min Act: -0.1700
Data Index: 1551756 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.1024. Min Act: -0.1700
Data Index: 2522089 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.0867. Min Act: -0.1700
Data Index: 7903117 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.0551. Min Act: -0.1700
Data Index: 160207 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.0551. Min Act: -0.1700
Data Index: 2581599 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.0551. Min Act: -0.1700
Data Index: 7270667 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.0709. Min Act: -0.1700
Data Index: 7600238 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.0394. Min Act: -0.1700
Data Index: 1166029 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.0394. Min Act: -0.1700
Data Index: 6835076 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.0394. Min Act: -0.1700
Data Index: 8562661 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.0078. Min Act: -0.1700
Data Index: 5593397 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.0236. Min Act: -0.1700
Data Index: 498087 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.0078. Min Act: -0.1700
Data Index: 4300678 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.0078. Min Act: -0.1700
Data Index: 1947336 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1812. Min Range: -3.1812
Max Act: 2.9920. Min Act: -0.1700
Data Index: 7710512 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1812. Min Range: -3.1812
Max Act: 3.0078. Min Act: -0.1700
Data Index: 5890225 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19