Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3289 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2500. Min Range: -6.2500
Max Act: 6.2500. Min Act: -0.1700
Data Index: 7773830 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2500. Min Range: -6.2500
Max Act: 6.2188. Min Act: -0.1700
Data Index: 1894212 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2500. Min Range: -6.2500
Max Act: 6.1875. Min Act: -0.1700
Data Index: 5773425 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2500. Min Range: -6.2500
Max Act: 6.1563. Min Act: -0.1700
Data Index: 743001 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2500. Min Range: -6.2500
Max Act: 6.1250. Min Act: -0.1700
Data Index: 8105254 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2500. Min Range: -6.2500
Max Act: 6.0313. Min Act: -0.1700
Data Index: 5526663 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2500. Min Range: -6.2500
Max Act: 6.0000. Min Act: -0.1700
Data Index: 4971077 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2500. Min Range: -6.2500
Max Act: 6.0000. Min Act: -0.1700
Data Index: 6015995 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2500. Min Range: -6.2500
Max Act: 6.0000. Min Act: -0.1700
Data Index: 4426561 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2500. Min Range: -6.2500
Max Act: 6.0000. Min Act: -0.1700
Data Index: 6563672 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2500. Min Range: -6.2500
Max Act: 6.0000. Min Act: -0.1700
Data Index: 5697673 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2500. Min Range: -6.2500
Max Act: 6.0000. Min Act: -0.1700
Data Index: 223610 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2500. Min Range: -6.2500
Max Act: 5.9688. Min Act: -0.1700
Data Index: 1625307 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2500. Min Range: -6.2500
Max Act: 6.0000. Min Act: -0.1700
Data Index: 515446 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2500. Min Range: -6.2500
Max Act: 5.9688. Min Act: -0.1700
Data Index: 7045274 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2500. Min Range: -6.2500
Max Act: 5.9375. Min Act: -0.1700
Data Index: 7857458 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2500. Min Range: -6.2500
Max Act: 5.9375. Min Act: -0.1700
Data Index: 7323442 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2500. Min Range: -6.2500
Max Act: 5.9688. Min Act: -0.1700
Data Index: 7601679 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2500. Min Range: -6.2500
Max Act: 5.9375. Min Act: -0.1700
Data Index: 458862 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2500. Min Range: -6.2500
Max Act: 5.9063. Min Act: -0.1700
Data Index: 5279321 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19