Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3820 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.9137. Min Act: -0.1700
Data Index: 2472608 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.7262. Min Act: -0.1700
Data Index: 7042280 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.7262. Min Act: -0.1700
Data Index: 3626304 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.6012. Min Act: -0.1700
Data Index: 3279915 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.6012. Min Act: -0.1700
Data Index: 286495 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.5700. Min Act: -0.1700
Data Index: 4500402 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.5387. Min Act: -0.1700
Data Index: 2403437 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.5075. Min Act: -0.1700
Data Index: 3265123 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.4450. Min Act: -0.1700
Data Index: 3527873 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.4450. Min Act: -0.1700
Data Index: 545798 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.4762. Min Act: -0.1700
Data Index: 5142450 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.4762. Min Act: -0.1700
Data Index: 882907 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.4137. Min Act: -0.1700
Data Index: 4919513 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.3825. Min Act: -0.1700
Data Index: 1350364 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.3512. Min Act: -0.1700
Data Index: 8024548 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.3512. Min Act: -0.1700
Data Index: 8634665 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.3512. Min Act: -0.1700
Data Index: 4220681 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.3512. Min Act: -0.1700
Data Index: 7830520 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.3512. Min Act: -0.1700
Data Index: 791239 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9137. Min Range: -6.9137
Max Act: 6.2887. Min Act: -0.1700
Data Index: 290005 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19