Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3836 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0889. Min Range: -4.0889
Max Act: 4.0889. Min Act: -0.1700
Data Index: 942978 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0889. Min Range: -4.0889
Max Act: 4.0264. Min Act: -0.1700
Data Index: 2000035 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0889. Min Range: -4.0889
Max Act: 4.0576. Min Act: -0.1700
Data Index: 6829172 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0889. Min Range: -4.0889
Max Act: 3.9951. Min Act: -0.1700
Data Index: 5477957 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0889. Min Range: -4.0889
Max Act: 3.9638. Min Act: -0.1700
Data Index: 4120389 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0889. Min Range: -4.0889
Max Act: 3.9638. Min Act: -0.1700
Data Index: 842273 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0889. Min Range: -4.0889
Max Act: 3.9326. Min Act: -0.1700
Data Index: 4081034 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0889. Min Range: -4.0889
Max Act: 3.9326. Min Act: -0.1700
Data Index: 8520030 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0889. Min Range: -4.0889
Max Act: 3.9013. Min Act: -0.1700
Data Index: 5046051 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0889. Min Range: -4.0889
Max Act: 3.9013. Min Act: -0.1700
Data Index: 6699204 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0889. Min Range: -4.0889
Max Act: 3.9013. Min Act: -0.1700
Data Index: 7954099 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0889. Min Range: -4.0889
Max Act: 3.8857. Min Act: -0.1700
Data Index: 6380558 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0889. Min Range: -4.0889
Max Act: 3.8544. Min Act: -0.1700
Data Index: 6584743 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0889. Min Range: -4.0889
Max Act: 3.8388. Min Act: -0.1700
Data Index: 5194655 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0889. Min Range: -4.0889
Max Act: 3.8075. Min Act: -0.1700
Data Index: 8454383 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0889. Min Range: -4.0889
Max Act: 3.8075. Min Act: -0.1700
Data Index: 4561541 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0889. Min Range: -4.0889
Max Act: 3.7919. Min Act: -0.1700
Data Index: 4535528 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0889. Min Range: -4.0889
Max Act: 3.7919. Min Act: -0.1700
Data Index: 7267197 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0889. Min Range: -4.0889
Max Act: 3.7762. Min Act: -0.1700
Data Index: 7899647 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0889. Min Range: -4.0889
Max Act: 3.7606. Min Act: -0.1700
Data Index: 5570169 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19