Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5116 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3644. Min Range: -7.3644
Max Act: 7.3644. Min Act: -0.1700
Data Index: 989466 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.8332. Min Act: -0.1700
Data Index: 3522254 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.7707. Min Act: -0.1700
Data Index: 6157719 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.6144. Min Act: -0.1700
Data Index: 3675275 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.5519. Min Act: -0.1700
Data Index: 2399323 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.5519. Min Act: -0.1700
Data Index: 2542679 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.5207. Min Act: -0.1700
Data Index: 6151893 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.4894. Min Act: -0.1700
Data Index: 7067890 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.4269. Min Act: -0.1700
Data Index: 7811233 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.4269. Min Act: -0.1700
Data Index: 7514553 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.3957. Min Act: -0.1700
Data Index: 4690187 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.3644. Min Act: -0.1700
Data Index: 130674 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.3957. Min Act: -0.1700
Data Index: 495786 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.3644. Min Act: -0.1700
Data Index: 1138155 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.3332. Min Act: -0.1700
Data Index: 6406158 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.3019. Min Act: -0.1700
Data Index: 3911188 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.2707. Min Act: -0.1700
Data Index: 1317969 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.2394. Min Act: -0.1700
Data Index: 2893932 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.2707. Min Act: -0.1700
Data Index: 807685 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3644. Min Range: -7.3644
Max Act: 6.2082. Min Act: -0.1700
Data Index: 5338870 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19