Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2934 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.9375. Min Act: -0.1700
Data Index: 1398460 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.8750. Min Act: -0.1700
Data Index: 1670523 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.7812. Min Act: -0.1700
Data Index: 183766 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.7500. Min Act: -0.1700
Data Index: 7357651 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.6875. Min Act: -0.1700
Data Index: 6277899 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.6562. Min Act: -0.1700
Data Index: 3434999 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.6250. Min Act: -0.1700
Data Index: 5315468 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.6250. Min Act: -0.1700
Data Index: 1356160 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.5937. Min Act: -0.1700
Data Index: 7729042 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.5937. Min Act: -0.1700
Data Index: 8363847 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.5937. Min Act: -0.1700
Data Index: 409003 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.5937. Min Act: -0.1700
Data Index: 112744 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.5625. Min Act: -0.1700
Data Index: 7090501 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.5312. Min Act: -0.1700
Data Index: 1568477 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.5000. Min Act: -0.1700
Data Index: 5712150 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.5000. Min Act: -0.1700
Data Index: 8691173 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.5000. Min Act: -0.1700
Data Index: 397981 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.5000. Min Act: -0.1700
Data Index: 5520820 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.4687. Min Act: -0.1700
Data Index: 6221586 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9375. Min Range: -5.9375
Max Act: 5.4375. Min Act: -0.1700
Data Index: 7616907 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19