Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2952 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.8873. Min Act: -0.1700
Data Index: 8793009 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.8247. Min Act: -0.1700
Data Index: 3944351 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.6683. Min Act: -0.1700
Data Index: 1963792 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.6057. Min Act: -0.1700
Data Index: 3010640 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.5744. Min Act: -0.1700
Data Index: 6782852 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.5744. Min Act: -0.1700
Data Index: 4349388 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.5431. Min Act: -0.1700
Data Index: 7137680 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.5431. Min Act: -0.1699
Data Index: 1946933 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.5431. Min Act: -0.1700
Data Index: 2441104 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.5431. Min Act: -0.1700
Data Index: 6614020 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.5431. Min Act: -0.1700
Data Index: 314705 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.5118. Min Act: -0.1700
Data Index: 5063352 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.4648. Min Act: -0.1700
Data Index: 184813 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.4648. Min Act: -0.1700
Data Index: 5559290 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.4648. Min Act: -0.1700
Data Index: 2879753 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.4491. Min Act: -0.1700
Data Index: 3034278 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.4805. Min Act: -0.1700
Data Index: 1598928 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.4491. Min Act: -0.1700
Data Index: 1263848 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.4178. Min Act: -0.1700
Data Index: 5656978 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8873. Min Range: -3.8873
Max Act: 3.4335. Min Act: -0.1700
Data Index: 4206759 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19