Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4788 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4844. Min Range: -6.4844
Max Act: 6.4844. Min Act: -0.1700
Data Index: 4758004 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4844. Min Range: -6.4844
Max Act: 6.4844. Min Act: -0.1700
Data Index: 1770555 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4844. Min Range: -6.4844
Max Act: 6.2969. Min Act: -0.1700
Data Index: 2020775 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4844. Min Range: -6.4844
Max Act: 6.1406. Min Act: -0.1700
Data Index: 1250109 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4844. Min Range: -6.4844
Max Act: 6.1094. Min Act: -0.1700
Data Index: 2251221 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4844. Min Range: -6.4844
Max Act: 6.0781. Min Act: -0.1700
Data Index: 2902356 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4844. Min Range: -6.4844
Max Act: 6.0781. Min Act: -0.1700
Data Index: 6146346 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4844. Min Range: -6.4844
Max Act: 6.0781. Min Act: -0.1700
Data Index: 2318315 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4844. Min Range: -6.4844
Max Act: 6.0469. Min Act: -0.1700
Data Index: 5116548 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4844. Min Range: -6.4844
Max Act: 6.0156. Min Act: -0.1700
Data Index: 5327295 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4844. Min Range: -6.4844
Max Act: 6.0156. Min Act: -0.1700
Data Index: 2958646 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4844. Min Range: -6.4844
Max Act: 5.9844. Min Act: -0.1700
Data Index: 6260603 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4844. Min Range: -6.4844
Max Act: 5.9844. Min Act: -0.1700
Data Index: 6903723 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4844. Min Range: -6.4844
Max Act: 5.9844. Min Act: -0.1700
Data Index: 7588501 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4844. Min Range: -6.4844
Max Act: 5.9844. Min Act: -0.1700
Data Index: 2115067 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4844. Min Range: -6.4844
Max Act: 5.9844. Min Act: -0.1700
Data Index: 5119884 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4844. Min Range: -6.4844
Max Act: 5.9844. Min Act: -0.1700
Data Index: 1757317 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4844. Min Range: -6.4844
Max Act: 5.9531. Min Act: -0.1700
Data Index: 99428 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4844. Min Range: -6.4844
Max Act: 5.9219. Min Act: -0.1700
Data Index: 2325472 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4844. Min Range: -6.4844
Max Act: 5.9219. Min Act: -0.1700
Data Index: 7143253 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19