Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2810 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3160. Min Range: -7.3160
Max Act: 7.3160. Min Act: -0.1700
Data Index: 1536147 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3160. Min Range: -7.3160
Max Act: 7.2535. Min Act: -0.1700
Data Index: 6117600 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3160. Min Range: -7.3160
Max Act: 7.1910. Min Act: -0.1700
Data Index: 6250576 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3160. Min Range: -7.3160
Max Act: 7.2222. Min Act: -0.1700
Data Index: 1208308 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3160. Min Range: -7.3160
Max Act: 7.1285. Min Act: -0.1700
Data Index: 1822772 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3160. Min Range: -7.3160
Max Act: 7.0035. Min Act: -0.1700
Data Index: 4034742 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3160. Min Range: -7.3160
Max Act: 6.9722. Min Act: -0.1700
Data Index: 2209275 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3160. Min Range: -7.3160
Max Act: 6.9722. Min Act: -0.1700
Data Index: 6021077 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3160. Min Range: -7.3160
Max Act: 6.9722. Min Act: -0.1700
Data Index: 8042606 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3160. Min Range: -7.3160
Max Act: 6.9410. Min Act: -0.1700
Data Index: 385676 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3160. Min Range: -7.3160
Max Act: 6.9410. Min Act: -0.1700
Data Index: 190808 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3160. Min Range: -7.3160
Max Act: 6.9097. Min Act: -0.1700
Data Index: 8201812 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3160. Min Range: -7.3160
Max Act: 6.9097. Min Act: -0.1700
Data Index: 4398849 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3160. Min Range: -7.3160
Max Act: 6.9097. Min Act: -0.1700
Data Index: 1430384 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3160. Min Range: -7.3160
Max Act: 6.9097. Min Act: -0.1700
Data Index: 7681445 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3160. Min Range: -7.3160
Max Act: 6.9097. Min Act: -0.1700
Data Index: 6559709 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3160. Min Range: -7.3160
Max Act: 6.8785. Min Act: -0.1700
Data Index: 5849140 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3160. Min Range: -7.3160
Max Act: 6.8472. Min Act: -0.1700
Data Index: 5957264 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3160. Min Range: -7.3160
Max Act: 6.8785. Min Act: -0.1700
Data Index: 3417484 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3160. Min Range: -7.3160
Max Act: 6.7847. Min Act: -0.1700
Data Index: 4804740 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19