Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1922 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.7800. Min Act: -0.1700
Data Index: 7323000 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.7481. Min Act: -0.1700
Data Index: 1035271 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.7321. Min Act: -0.1700
Data Index: 4746576 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.6681. Min Act: -0.1700
Data Index: 2847743 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.6360. Min Act: -0.1700
Data Index: 6271359 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.6360. Min Act: -0.1700
Data Index: 6386328 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.6200. Min Act: -0.1700
Data Index: 2650278 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.6200. Min Act: -0.1700
Data Index: 18000 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.5878. Min Act: -0.1700
Data Index: 3327313 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.5878. Min Act: -0.1700
Data Index: 2503012 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.5878. Min Act: -0.1700
Data Index: 2699816 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.5717. Min Act: -0.1700
Data Index: 3840809 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.5555. Min Act: -0.1700
Data Index: 8477532 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.5717. Min Act: -0.1700
Data Index: 1748215 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.5555. Min Act: -0.1700
Data Index: 8412418 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.5394. Min Act: -0.1700
Data Index: 3872752 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.5555. Min Act: -0.1700
Data Index: 1572697 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.5717. Min Act: -0.1700
Data Index: 4699851 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.5232. Min Act: -0.1700
Data Index: 6503406 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7800. Min Range: -2.7800
Max Act: 2.5232. Min Act: -0.1700
Data Index: 6651124 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19