Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5592 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0003. Min Range: -5.0003
Max Act: 5.0003. Min Act: -0.1700
Data Index: 5394435 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.8753. Min Act: -0.1700
Data Index: 8307547 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.8753. Min Act: -0.1700
Data Index: 2360198 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.8753. Min Act: -0.1700
Data Index: 2773956 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.8753. Min Act: -0.1700
Data Index: 7793391 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.8440. Min Act: -0.1700
Data Index: 8180777 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.8128. Min Act: -0.1700
Data Index: 1549992 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.8128. Min Act: -0.1700
Data Index: 5170197 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.8128. Min Act: -0.1700
Data Index: 3568121 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.7815. Min Act: -0.1700
Data Index: 6099520 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.7815. Min Act: -0.1700
Data Index: 467244 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.7503. Min Act: -0.1700
Data Index: 8099363 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.7815. Min Act: -0.1700
Data Index: 1045535 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.7815. Min Act: -0.1700
Data Index: 195853 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.7503. Min Act: -0.1700
Data Index: 3083702 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.7503. Min Act: -0.1700
Data Index: 6172864 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.7190. Min Act: -0.1700
Data Index: 3315261 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.7190. Min Act: -0.1700
Data Index: 6450233 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.7190. Min Act: -0.1700
Data Index: 6686176 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0003. Min Range: -5.0003
Max Act: 4.6878. Min Act: -0.1700
Data Index: 7537624 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19