Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 952 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.7017. Min Act: -0.1700
Data Index: 6571070 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.5142. Min Act: -0.1700
Data Index: 639230 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.3580. Min Act: -0.1700
Data Index: 725482 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.3267. Min Act: -0.1700
Data Index: 6242370 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.3580. Min Act: -0.1700
Data Index: 4034515 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.3580. Min Act: -0.1700
Data Index: 8476798 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.3267. Min Act: -0.1700
Data Index: 5465458 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.3267. Min Act: -0.1700
Data Index: 302337 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.3267. Min Act: -0.1700
Data Index: 3620588 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.3267. Min Act: -0.1700
Data Index: 1783809 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.3267. Min Act: -0.1700
Data Index: 4105847 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.3267. Min Act: -0.1700
Data Index: 256324 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.3267. Min Act: -0.1700
Data Index: 1334262 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.3267. Min Act: -0.1700
Data Index: 2803088 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.2955. Min Act: -0.1700
Data Index: 2341967 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.2955. Min Act: -0.1700
Data Index: 3607585 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.2955. Min Act: -0.1700
Data Index: 161666 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.2642. Min Act: -0.1700
Data Index: 8169814 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.2955. Min Act: -0.1700
Data Index: 5297645 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7017. Min Range: -4.7017
Max Act: 4.2642. Min Act: -0.1700
Data Index: 7003900 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19