Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3637 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6328. Min Range: -7.6328
Max Act: 7.6328. Min Act: -0.1700
Data Index: 2994959 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6328. Min Range: -7.6328
Max Act: 7.3203. Min Act: -0.1700
Data Index: 1649906 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6328. Min Range: -7.6328
Max Act: 7.2578. Min Act: -0.1700
Data Index: 3800625 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6328. Min Range: -7.6328
Max Act: 7.2578. Min Act: -0.1700
Data Index: 1108419 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6328. Min Range: -7.6328
Max Act: 7.2265. Min Act: -0.1700
Data Index: 7330580 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6328. Min Range: -7.6328
Max Act: 7.1640. Min Act: -0.1700
Data Index: 3851469 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6328. Min Range: -7.6328
Max Act: 7.1328. Min Act: -0.1700
Data Index: 5781078 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6328. Min Range: -7.6328
Max Act: 7.1015. Min Act: -0.1700
Data Index: 7401525 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6328. Min Range: -7.6328
Max Act: 7.0703. Min Act: -0.1700
Data Index: 593049 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6328. Min Range: -7.6328
Max Act: 7.0703. Min Act: -0.1700
Data Index: 4074813 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6328. Min Range: -7.6328
Max Act: 7.0390. Min Act: -0.1700
Data Index: 8068517 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6328. Min Range: -7.6328
Max Act: 6.9765. Min Act: -0.1700
Data Index: 6194380 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6328. Min Range: -7.6328
Max Act: 6.9453. Min Act: -0.1700
Data Index: 4383028 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6328. Min Range: -7.6328
Max Act: 6.9453. Min Act: -0.1700
Data Index: 7729501 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6328. Min Range: -7.6328
Max Act: 6.9453. Min Act: -0.1700
Data Index: 2613855 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6328. Min Range: -7.6328
Max Act: 6.9453. Min Act: -0.1700
Data Index: 7109233 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6328. Min Range: -7.6328
Max Act: 6.9140. Min Act: -0.1700
Data Index: 4402236 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6328. Min Range: -7.6328
Max Act: 6.9140. Min Act: -0.1700
Data Index: 6729953 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6328. Min Range: -7.6328
Max Act: 6.9140. Min Act: -0.1700
Data Index: 6721187 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6328. Min Range: -7.6328
Max Act: 6.8515. Min Act: -0.1700
Data Index: 7455719 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19