Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2474 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.4430. Min Act: -0.1700
Data Index: 4323327 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.4117. Min Act: -0.1700
Data Index: 5183389 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.3960. Min Act: -0.1700
Data Index: 3497136 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.3803. Min Act: -0.1700
Data Index: 5781323 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.3489. Min Act: -0.1700
Data Index: 7272637 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.3489. Min Act: -0.1700
Data Index: 5615584 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.3489. Min Act: -0.1700
Data Index: 5271880 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.3332. Min Act: -0.1700
Data Index: 1469785 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.3176. Min Act: -0.1700
Data Index: 262794 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.3176. Min Act: -0.1700
Data Index: 1742243 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.3176. Min Act: -0.1700
Data Index: 5158095 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.3019. Min Act: -0.1700
Data Index: 8674681 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.3019. Min Act: -0.1700
Data Index: 1035846 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.3019. Min Act: -0.1700
Data Index: 233352 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.3176. Min Act: -0.1700
Data Index: 6510050 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.2862. Min Act: -0.1700
Data Index: 6862511 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.2862. Min Act: -0.1700
Data Index: 372018 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.2862. Min Act: -0.1700
Data Index: 6138194 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.2862. Min Act: -0.1700
Data Index: 1469790 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4430. Min Range: -3.4430
Max Act: 3.2862. Min Act: -0.1700
Data Index: 11293 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19