Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 314 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5201. Min Range: -6.5201
Max Act: 6.5201. Min Act: -0.1700
Data Index: 4897960 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5201. Min Range: -6.5201
Max Act: 6.3951. Min Act: -0.1700
Data Index: 3120330 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5201. Min Range: -6.5201
Max Act: 6.2389. Min Act: -0.1700
Data Index: 8048031 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5201. Min Range: -6.5201
Max Act: 6.2076. Min Act: -0.1700
Data Index: 7037874 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5201. Min Range: -6.5201
Max Act: 6.1764. Min Act: -0.1700
Data Index: 3642446 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5201. Min Range: -6.5201
Max Act: 6.1451. Min Act: -0.1700
Data Index: 6266130 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5201. Min Range: -6.5201
Max Act: 6.1139. Min Act: -0.1700
Data Index: 3155472 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5201. Min Range: -6.5201
Max Act: 6.1139. Min Act: -0.1700
Data Index: 3571616 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5201. Min Range: -6.5201
Max Act: 6.0514. Min Act: -0.1700
Data Index: 1947941 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5201. Min Range: -6.5201
Max Act: 6.0826. Min Act: -0.1700
Data Index: 4307357 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5201. Min Range: -6.5201
Max Act: 6.0826. Min Act: -0.1700
Data Index: 1178323 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5201. Min Range: -6.5201
Max Act: 6.0826. Min Act: -0.1700
Data Index: 2385952 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5201. Min Range: -6.5201
Max Act: 6.0514. Min Act: -0.1700
Data Index: 236092 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5201. Min Range: -6.5201
Max Act: 6.0201. Min Act: -0.1700
Data Index: 3450945 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5201. Min Range: -6.5201
Max Act: 5.9576. Min Act: -0.1700
Data Index: 655873 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5201. Min Range: -6.5201
Max Act: 6.0201. Min Act: -0.1700
Data Index: 4760261 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5201. Min Range: -6.5201
Max Act: 6.0201. Min Act: -0.1700
Data Index: 4548825 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5201. Min Range: -6.5201
Max Act: 5.9264. Min Act: -0.1700
Data Index: 624332 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5201. Min Range: -6.5201
Max Act: 5.8951. Min Act: -0.1700
Data Index: 2557803 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5201. Min Range: -6.5201
Max Act: 5.9264. Min Act: -0.1700
Data Index: 2087918 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19