Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5036 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2013. Min Range: -7.2013
Max Act: 7.2013. Min Act: -0.1700
Data Index: 8711676 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2013. Min Range: -7.2013
Max Act: 7.0763. Min Act: -0.1700
Data Index: 4881610 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.8888. Min Act: -0.1700
Data Index: 3727655 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.8263. Min Act: -0.1700
Data Index: 4972053 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.8263. Min Act: -0.1700
Data Index: 2638747 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.8263. Min Act: -0.1700
Data Index: 1181375 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.8263. Min Act: -0.1700
Data Index: 2357295 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.7951. Min Act: -0.1700
Data Index: 5163684 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.7951. Min Act: -0.1700
Data Index: 312451 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.7951. Min Act: -0.1700
Data Index: 533175 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.7951. Min Act: -0.1700
Data Index: 4003995 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.7951. Min Act: -0.1700
Data Index: 1950806 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.7951. Min Act: -0.1700
Data Index: 7631567 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.7638. Min Act: -0.1700
Data Index: 4894263 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.7638. Min Act: -0.1700
Data Index: 8653977 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.7638. Min Act: -0.1700
Data Index: 2428469 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.7638. Min Act: -0.1700
Data Index: 4795862 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.7638. Min Act: -0.1700
Data Index: 4532006 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.7638. Min Act: -0.1700
Data Index: 2405220 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2013. Min Range: -7.2013
Max Act: 6.7638. Min Act: -0.1700
Data Index: 898703 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19