Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1425 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2505. Min Range: -6.2505
Max Act: 6.2505. Min Act: -0.1700
Data Index: 8567827 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2505. Min Range: -6.2505
Max Act: 6.2192. Min Act: -0.1700
Data Index: 1881458 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2505. Min Range: -6.2505
Max Act: 6.0630. Min Act: -0.1700
Data Index: 8766224 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2505. Min Range: -6.2505
Max Act: 6.0317. Min Act: -0.1700
Data Index: 5007281 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2505. Min Range: -6.2505
Max Act: 6.0005. Min Act: -0.1700
Data Index: 392191 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2505. Min Range: -6.2505
Max Act: 6.0630. Min Act: -0.1700
Data Index: 1685620 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2505. Min Range: -6.2505
Max Act: 6.0317. Min Act: -0.1700
Data Index: 635848 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2505. Min Range: -6.2505
Max Act: 6.0005. Min Act: -0.1700
Data Index: 1131180 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2505. Min Range: -6.2505
Max Act: 5.9692. Min Act: -0.1700
Data Index: 8766239 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2505. Min Range: -6.2505
Max Act: 5.9380. Min Act: -0.1700
Data Index: 5471390 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2505. Min Range: -6.2505
Max Act: 5.9380. Min Act: -0.1700
Data Index: 2589677 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2505. Min Range: -6.2505
Max Act: 5.9067. Min Act: -0.1700
Data Index: 6787530 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2505. Min Range: -6.2505
Max Act: 5.8755. Min Act: -0.1700
Data Index: 2424983 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2505. Min Range: -6.2505
Max Act: 5.8442. Min Act: -0.1700
Data Index: 3075520 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2505. Min Range: -6.2505
Max Act: 5.8755. Min Act: -0.1700
Data Index: 708228 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2505. Min Range: -6.2505
Max Act: 5.8755. Min Act: -0.1700
Data Index: 281681 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2505. Min Range: -6.2505
Max Act: 5.8442. Min Act: -0.1700
Data Index: 8575533 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2505. Min Range: -6.2505
Max Act: 5.8442. Min Act: -0.1700
Data Index: 3016848 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2505. Min Range: -6.2505
Max Act: 5.8442. Min Act: -0.1700
Data Index: 2650884 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2505. Min Range: -6.2505
Max Act: 5.8130. Min Act: -0.1700
Data Index: 2175854 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19