Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6126 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.6203. Min Act: -0.1700
Data Index: 5172873 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.4641. Min Act: -0.1700
Data Index: 3015479 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.4641. Min Act: -0.1699
Data Index: 265237 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.4641. Min Act: -0.1700
Data Index: 5497677 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.3703. Min Act: -0.1700
Data Index: 5128295 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.4016. Min Act: -0.1700
Data Index: 2880508 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.3078. Min Act: -0.1700
Data Index: 4263670 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.3078. Min Act: -0.1700
Data Index: 477780 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.2766. Min Act: -0.1700
Data Index: 7789767 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.2766. Min Act: -0.1700
Data Index: 236003 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.2453. Min Act: -0.1700
Data Index: 3422660 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.2453. Min Act: -0.1700
Data Index: 236002 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.2453. Min Act: -0.1700
Data Index: 2304612 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.2453. Min Act: -0.1700
Data Index: 2249367 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.2453. Min Act: -0.1700
Data Index: 4529625 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.2453. Min Act: -0.1700
Data Index: 114023 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.2453. Min Act: -0.1700
Data Index: 5783494 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.2141. Min Act: -0.1700
Data Index: 704131 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.2141. Min Act: -0.1700
Data Index: 1616167 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6203. Min Range: -6.6203
Max Act: 6.1828. Min Act: -0.1700
Data Index: 4810487 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19