Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4518 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.6444. Min Act: -0.1700
Data Index: 6260447 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.6131. Min Act: -0.1700
Data Index: 677844 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.5819. Min Act: -0.1700
Data Index: 5631400 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.5506. Min Act: -0.1700
Data Index: 8104473 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.5506. Min Act: -0.1700
Data Index: 2222074 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.5194. Min Act: -0.1700
Data Index: 8201976 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.5506. Min Act: -0.1700
Data Index: 1719959 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.5194. Min Act: -0.1700
Data Index: 2108545 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.4881. Min Act: -0.1700
Data Index: 6766483 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.4256. Min Act: -0.1700
Data Index: 4045489 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.4569. Min Act: -0.1700
Data Index: 6888456 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.3944. Min Act: -0.1700
Data Index: 3273792 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.3944. Min Act: -0.1700
Data Index: 5702218 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.3631. Min Act: -0.1700
Data Index: 733280 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.3631. Min Act: -0.1700
Data Index: 1949074 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.3319. Min Act: -0.1700
Data Index: 4297876 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.3631. Min Act: -0.1700
Data Index: 7511699 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.3319. Min Act: -0.1700
Data Index: 1468219 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.3631. Min Act: -0.1700
Data Index: 5066464 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6444. Min Range: -6.6444
Max Act: 6.3631. Min Act: -0.1700
Data Index: 6832420 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19