Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3442 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1817. Min Range: -6.1817
Max Act: 6.1817. Min Act: -0.1700
Data Index: 7514544 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.7755. Min Act: -0.1700
Data Index: 5771628 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.6505. Min Act: -0.1700
Data Index: 87646 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.6192. Min Act: -0.1700
Data Index: 5448994 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.6192. Min Act: -0.1700
Data Index: 5876836 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.5880. Min Act: -0.1700
Data Index: 7869232 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.5880. Min Act: -0.1700
Data Index: 2777172 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.5880. Min Act: -0.1700
Data Index: 6484502 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.5880. Min Act: -0.1700
Data Index: 7891444 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.5567. Min Act: -0.1700
Data Index: 4087270 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.5255. Min Act: -0.1700
Data Index: 1674694 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.5255. Min Act: -0.1700
Data Index: 3141368 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.4942. Min Act: -0.1700
Data Index: 4311915 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.4630. Min Act: -0.1700
Data Index: 6585207 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.4630. Min Act: -0.1700
Data Index: 7306589 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.4630. Min Act: -0.1700
Data Index: 7813148 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.4317. Min Act: -0.1700
Data Index: 4432774 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.4005. Min Act: -0.1700
Data Index: 1119903 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.4005. Min Act: -0.1700
Data Index: 1168719 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1817. Min Range: -6.1817
Max Act: 5.4005. Min Act: -0.1699
Data Index: 1402910 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19