Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4754 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4705. Min Range: -6.4705
Max Act: 6.4705. Min Act: -0.1700
Data Index: 8048223 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4705. Min Range: -6.4705
Max Act: 6.3768. Min Act: -0.1700
Data Index: 4609737 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4705. Min Range: -6.4705
Max Act: 6.3455. Min Act: -0.1700
Data Index: 5791433 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4705. Min Range: -6.4705
Max Act: 6.1580. Min Act: -0.1700
Data Index: 8048226 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4705. Min Range: -6.4705
Max Act: 6.1580. Min Act: -0.1700
Data Index: 1328308 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4705. Min Range: -6.4705
Max Act: 6.0955. Min Act: -0.1700
Data Index: 4401314 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4705. Min Range: -6.4705
Max Act: 6.0643. Min Act: -0.1700
Data Index: 53417 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4705. Min Range: -6.4705
Max Act: 6.0330. Min Act: -0.1700
Data Index: 7245078 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4705. Min Range: -6.4705
Max Act: 6.0330. Min Act: -0.1700
Data Index: 1860038 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4705. Min Range: -6.4705
Max Act: 6.0018. Min Act: -0.1700
Data Index: 4224854 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4705. Min Range: -6.4705
Max Act: 5.9705. Min Act: -0.1700
Data Index: 8577948 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4705. Min Range: -6.4705
Max Act: 5.9705. Min Act: -0.1700
Data Index: 237563 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4705. Min Range: -6.4705
Max Act: 5.9393. Min Act: -0.1700
Data Index: 2198745 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4705. Min Range: -6.4705
Max Act: 5.9393. Min Act: -0.1700
Data Index: 5767679 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4705. Min Range: -6.4705
Max Act: 5.9393. Min Act: -0.1700
Data Index: 3004753 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4705. Min Range: -6.4705
Max Act: 5.9393. Min Act: -0.1700
Data Index: 8328956 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4705. Min Range: -6.4705
Max Act: 5.9393. Min Act: -0.1700
Data Index: 8048227 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4705. Min Range: -6.4705
Max Act: 5.9080. Min Act: -0.1700
Data Index: 1834731 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4705. Min Range: -6.4705
Max Act: 5.8768. Min Act: -0.1700
Data Index: 4523415 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4705. Min Range: -6.4705
Max Act: 5.9393. Min Act: -0.1700
Data Index: 826443 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19