Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3164 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.6033. Min Act: -0.1700
Data Index: 5293699 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.5720. Min Act: -0.1700
Data Index: 8599178 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.4783. Min Act: -0.1700
Data Index: 2420269 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.4470. Min Act: -0.1700
Data Index: 5312750 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.3533. Min Act: -0.1700
Data Index: 4487555 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.3845. Min Act: -0.1700
Data Index: 2019938 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.3533. Min Act: -0.1700
Data Index: 7646778 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.3845. Min Act: -0.1700
Data Index: 2263155 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.4158. Min Act: -0.1700
Data Index: 5995341 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.3220. Min Act: -0.1700
Data Index: 3391225 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.3220. Min Act: -0.1700
Data Index: 1170783 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.3220. Min Act: -0.1700
Data Index: 5488127 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.3220. Min Act: -0.1700
Data Index: 4705893 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.3533. Min Act: -0.1700
Data Index: 8556285 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.3220. Min Act: -0.1700
Data Index: 6183997 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.2908. Min Act: -0.1700
Data Index: 7672889 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.2595. Min Act: -0.1700
Data Index: 4059712 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.2595. Min Act: -0.1700
Data Index: 6913218 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.2283. Min Act: -0.1700
Data Index: 1207728 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6033. Min Range: -6.6033
Max Act: 6.1970. Min Act: -0.1700
Data Index: 1029434 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19