Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2769 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0706. Min Range: -3.0706
Max Act: 3.0706. Min Act: -0.1700
Data Index: 7010791 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0706. Min Range: -3.0706
Max Act: 3.0548. Min Act: -0.1700
Data Index: 138606 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0706. Min Range: -3.0706
Max Act: 3.0390. Min Act: -0.1700
Data Index: 6028656 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0706. Min Range: -3.0706
Max Act: 3.0232. Min Act: -0.1700
Data Index: 2345056 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0706. Min Range: -3.0706
Max Act: 2.9916. Min Act: -0.1700
Data Index: 4452977 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0706. Min Range: -3.0706
Max Act: 2.9758. Min Act: -0.1700
Data Index: 5218293 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0706. Min Range: -3.0706
Max Act: 2.9600. Min Act: -0.1700
Data Index: 5076857 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0706. Min Range: -3.0706
Max Act: 2.9600. Min Act: -0.1700
Data Index: 4262068 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0706. Min Range: -3.0706
Max Act: 2.9442. Min Act: -0.1700
Data Index: 7536666 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0706. Min Range: -3.0706
Max Act: 2.9442. Min Act: -0.1700
Data Index: 2207674 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0706. Min Range: -3.0706
Max Act: 2.9442. Min Act: -0.1700
Data Index: 3526685 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0706. Min Range: -3.0706
Max Act: 2.9442. Min Act: -0.1700
Data Index: 3522038 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0706. Min Range: -3.0706
Max Act: 2.9283. Min Act: -0.1700
Data Index: 5854852 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0706. Min Range: -3.0706
Max Act: 2.9283. Min Act: -0.1700
Data Index: 5821306 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0706. Min Range: -3.0706
Max Act: 2.9283. Min Act: -0.1700
Data Index: 913000 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0706. Min Range: -3.0706
Max Act: 2.9283. Min Act: -0.1700
Data Index: 6374850 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0706. Min Range: -3.0706
Max Act: 2.9283. Min Act: -0.1700
Data Index: 5585829 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0706. Min Range: -3.0706
Max Act: 2.9283. Min Act: -0.1700
Data Index: 7010220 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0706. Min Range: -3.0706
Max Act: 2.9125. Min Act: -0.1700
Data Index: 6182422 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0706. Min Range: -3.0706
Max Act: 2.9442. Min Act: -0.1700
Data Index: 3842564 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19