Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 627 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3469. Min Range: -5.3469
Max Act: 5.3469. Min Act: -0.1700
Data Index: 8496172 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3469. Min Range: -5.3469
Max Act: 5.2531. Min Act: -0.1700
Data Index: 1127183 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3469. Min Range: -5.3469
Max Act: 5.1906. Min Act: -0.1700
Data Index: 6405208 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3469. Min Range: -5.3469
Max Act: 5.1281. Min Act: -0.1700
Data Index: 5666923 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3469. Min Range: -5.3469
Max Act: 5.0969. Min Act: -0.1700
Data Index: 5020311 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3469. Min Range: -5.3469
Max Act: 5.0031. Min Act: -0.1700
Data Index: 5995580 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3469. Min Range: -5.3469
Max Act: 4.9406. Min Act: -0.1700
Data Index: 7640071 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3469. Min Range: -5.3469
Max Act: 4.9406. Min Act: -0.1700
Data Index: 4939175 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3469. Min Range: -5.3469
Max Act: 4.9406. Min Act: -0.1700
Data Index: 3497596 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3469. Min Range: -5.3469
Max Act: 4.9094. Min Act: -0.1700
Data Index: 4162257 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3469. Min Range: -5.3469
Max Act: 4.9406. Min Act: -0.1700
Data Index: 6445518 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3469. Min Range: -5.3469
Max Act: 4.9094. Min Act: -0.1700
Data Index: 6296658 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3469. Min Range: -5.3469
Max Act: 4.9094. Min Act: -0.1700
Data Index: 6349084 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3469. Min Range: -5.3469
Max Act: 4.9094. Min Act: -0.1700
Data Index: 5320134 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3469. Min Range: -5.3469
Max Act: 4.8781. Min Act: -0.1700
Data Index: 5339250 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3469. Min Range: -5.3469
Max Act: 4.8156. Min Act: -0.1700
Data Index: 3236254 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3469. Min Range: -5.3469
Max Act: 4.8156. Min Act: -0.1700
Data Index: 611879 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3469. Min Range: -5.3469
Max Act: 4.7844. Min Act: -0.1700
Data Index: 7572663 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3469. Min Range: -5.3469
Max Act: 4.7531. Min Act: -0.1700
Data Index: 3333356 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3469. Min Range: -5.3469
Max Act: 4.6906. Min Act: -0.1700
Data Index: 5833538 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19