Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4021 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.3495. Min Act: -0.1700
Data Index: 4962248 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.3495. Min Act: -0.1700
Data Index: 2253444 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.3495. Min Act: -0.1700
Data Index: 1884400 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.3183. Min Act: -0.1700
Data Index: 1776689 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.3183. Min Act: -0.1700
Data Index: 8682762 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.3183. Min Act: -0.1700
Data Index: 8445303 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.2870. Min Act: -0.1700
Data Index: 2428986 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.3183. Min Act: -0.1700
Data Index: 918753 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.2870. Min Act: -0.1700
Data Index: 7449076 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.2870. Min Act: -0.1700
Data Index: 6769380 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.2558. Min Act: -0.1700
Data Index: 7690518 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.3183. Min Act: -0.1700
Data Index: 5120917 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.2558. Min Act: -0.1700
Data Index: 462585 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.2558. Min Act: -0.1700
Data Index: 8642108 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.2558. Min Act: -0.1700
Data Index: 7662011 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.2558. Min Act: -0.1700
Data Index: 4432803 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.2558. Min Act: -0.1700
Data Index: 4041577 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.2558. Min Act: -0.1700
Data Index: 2741618 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.2245. Min Act: -0.1700
Data Index: 673693 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3495. Min Range: -6.3495
Max Act: 6.2245. Min Act: -0.1700
Data Index: 2547828 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19