Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2905 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.5628. Min Act: -0.1700
Data Index: 2722337 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.5315. Min Act: -0.1700
Data Index: 1476704 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.5315. Min Act: -0.1700
Data Index: 385693 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.5158. Min Act: -0.1700
Data Index: 5248488 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.4218. Min Act: -0.1700
Data Index: 6414012 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.4375. Min Act: -0.1700
Data Index: 3561598 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.4218. Min Act: -0.1700
Data Index: 2203335 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.4218. Min Act: -0.1700
Data Index: 1630561 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.4375. Min Act: -0.1700
Data Index: 4650984 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.4218. Min Act: -0.1700
Data Index: 3180876 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.3904. Min Act: -0.1700
Data Index: 4254860 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.4218. Min Act: -0.1700
Data Index: 3484496 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.3904. Min Act: -0.1700
Data Index: 7561305 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.3748. Min Act: -0.1700
Data Index: 152312 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.3591. Min Act: -0.1700
Data Index: 4963364 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.3434. Min Act: -0.1700
Data Index: 5086712 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.3434. Min Act: -0.1700
Data Index: 4030195 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.3434. Min Act: -0.1700
Data Index: 3165120 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.3434. Min Act: -0.1700
Data Index: 1003873 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5628. Min Range: -3.5628
Max Act: 3.3434. Min Act: -0.1700
Data Index: 95787 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19