Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1790 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.6936. Min Act: -0.1700
Data Index: 1846444 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.6936. Min Act: -0.1700
Data Index: 1476054 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.4749. Min Act: -0.1700
Data Index: 371555 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.4436. Min Act: -0.1700
Data Index: 4895624 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.3499. Min Act: -0.1700
Data Index: 4803475 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.2874. Min Act: -0.1700
Data Index: 1485966 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.2249. Min Act: -0.1700
Data Index: 6179747 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.1936. Min Act: -0.1700
Data Index: 391027 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.1936. Min Act: -0.1700
Data Index: 7381427 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.1936. Min Act: -0.1700
Data Index: 2443031 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.1624. Min Act: -0.1700
Data Index: 7574012 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.1624. Min Act: -0.1700
Data Index: 8041468 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.0686. Min Act: -0.1700
Data Index: 5727464 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.0686. Min Act: -0.1700
Data Index: 1859236 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.0686. Min Act: -0.1700
Data Index: 4094868 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.0374. Min Act: -0.1700
Data Index: 7594674 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.0374. Min Act: -0.1700
Data Index: 7514724 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.0374. Min Act: -0.1700
Data Index: 8704287 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.0374. Min Act: -0.1700
Data Index: 1895472 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6936. Min Range: -7.6936
Max Act: 7.0061. Min Act: -0.1700
Data Index: 4852002 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19