Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4322 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0211. Min Range: -6.0211
Max Act: 6.0211. Min Act: -0.1700
Data Index: 4894969 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0211. Min Range: -6.0211
Max Act: 6.0211. Min Act: -0.1700
Data Index: 4339715 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.9586. Min Act: -0.1700
Data Index: 63112 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.8649. Min Act: -0.1700
Data Index: 2796871 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.7399. Min Act: -0.1700
Data Index: 2530988 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.7086. Min Act: -0.1700
Data Index: 1553660 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.7399. Min Act: -0.1700
Data Index: 2580350 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.7086. Min Act: -0.1700
Data Index: 5727849 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.7086. Min Act: -0.1700
Data Index: 7962652 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.6774. Min Act: -0.1700
Data Index: 539255 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.6774. Min Act: -0.1700
Data Index: 8098190 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.6461. Min Act: -0.1700
Data Index: 4719645 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.6461. Min Act: -0.1700
Data Index: 5629945 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.6461. Min Act: -0.1700
Data Index: 5420507 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.6461. Min Act: -0.1700
Data Index: 7481483 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.6461. Min Act: -0.1700
Data Index: 5882363 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.6461. Min Act: -0.1700
Data Index: 4408568 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.5836. Min Act: -0.1700
Data Index: 3435473 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.6149. Min Act: -0.1700
Data Index: 3661834 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0211. Min Range: -6.0211
Max Act: 5.5836. Min Act: -0.1700
Data Index: 2580372 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19