Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2230 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8847. Min Range: -6.8847
Max Act: 6.8847. Min Act: -0.1700
Data Index: 2467535 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8847. Min Range: -6.8847
Max Act: 6.5722. Min Act: -0.1700
Data Index: 8539705 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8847. Min Range: -6.8847
Max Act: 6.2910. Min Act: -0.1700
Data Index: 493196 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8847. Min Range: -6.8847
Max Act: 6.2285. Min Act: -0.1700
Data Index: 4901482 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8847. Min Range: -6.8847
Max Act: 6.1035. Min Act: -0.1700
Data Index: 3437535 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8847. Min Range: -6.8847
Max Act: 6.1347. Min Act: -0.1700
Data Index: 439200 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8847. Min Range: -6.8847
Max Act: 6.0722. Min Act: -0.1700
Data Index: 219826 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8847. Min Range: -6.8847
Max Act: 6.0410. Min Act: -0.1700
Data Index: 6428205 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8847. Min Range: -6.8847
Max Act: 6.0097. Min Act: -0.1700
Data Index: 8630557 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8847. Min Range: -6.8847
Max Act: 5.9785. Min Act: -0.1700
Data Index: 68223 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8847. Min Range: -6.8847
Max Act: 5.9160. Min Act: -0.1700
Data Index: 7792565 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8847. Min Range: -6.8847
Max Act: 5.9160. Min Act: -0.1700
Data Index: 3097758 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8847. Min Range: -6.8847
Max Act: 5.9160. Min Act: -0.1700
Data Index: 8104307 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8847. Min Range: -6.8847
Max Act: 5.8535. Min Act: -0.1700
Data Index: 1954109 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8847. Min Range: -6.8847
Max Act: 5.8847. Min Act: -0.1700
Data Index: 8544941 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8847. Min Range: -6.8847
Max Act: 5.8222. Min Act: -0.1700
Data Index: 1996071 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8847. Min Range: -6.8847
Max Act: 5.8222. Min Act: -0.1700
Data Index: 8544953 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8847. Min Range: -6.8847
Max Act: 5.8222. Min Act: -0.1700
Data Index: 6957034 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8847. Min Range: -6.8847
Max Act: 5.7910. Min Act: -0.1700
Data Index: 3615488 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8847. Min Range: -6.8847
Max Act: 5.8222. Min Act: -0.1700
Data Index: 5201698 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19