Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 75 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4045. Min Range: -6.4045
Max Act: 6.4045. Min Act: -0.1700
Data Index: 8829254 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.9045. Min Act: -0.1700
Data Index: 4386892 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.9045. Min Act: -0.1700
Data Index: 5787576 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.8420. Min Act: -0.1700
Data Index: 3108758 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.7170. Min Act: -0.1700
Data Index: 352460 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.6858. Min Act: -0.1700
Data Index: 4340780 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.6858. Min Act: -0.1700
Data Index: 2285000 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.6858. Min Act: -0.1700
Data Index: 7670917 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.6545. Min Act: -0.1700
Data Index: 4747006 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.6545. Min Act: -0.1700
Data Index: 2772700 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.6545. Min Act: -0.1700
Data Index: 5692978 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.6233. Min Act: -0.1700
Data Index: 6183791 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.6233. Min Act: -0.1700
Data Index: 6228583 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.6233. Min Act: -0.1700
Data Index: 5492359 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.6233. Min Act: -0.1700
Data Index: 8506817 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.5920. Min Act: -0.1700
Data Index: 7841778 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.5920. Min Act: -0.1700
Data Index: 5921964 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.5608. Min Act: -0.1700
Data Index: 1265088 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.5295. Min Act: -0.1700
Data Index: 6249265 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4045. Min Range: -6.4045
Max Act: 5.5608. Min Act: -0.1700
Data Index: 5108886 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19