Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1857 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2716. Min Range: -6.2716
Max Act: 6.2716. Min Act: -0.1700
Data Index: 1324417 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2716. Min Range: -6.2716
Max Act: 6.1778. Min Act: -0.1700
Data Index: 5713705 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2716. Min Range: -6.2716
Max Act: 6.0216. Min Act: -0.1700
Data Index: 296276 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2716. Min Range: -6.2716
Max Act: 5.9278. Min Act: -0.1700
Data Index: 1603232 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2716. Min Range: -6.2716
Max Act: 5.8966. Min Act: -0.1700
Data Index: 1138092 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2716. Min Range: -6.2716
Max Act: 5.8653. Min Act: -0.1700
Data Index: 977970 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2716. Min Range: -6.2716
Max Act: 5.8653. Min Act: -0.1700
Data Index: 3131347 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2716. Min Range: -6.2716
Max Act: 5.8653. Min Act: -0.1700
Data Index: 1331109 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2716. Min Range: -6.2716
Max Act: 5.8653. Min Act: -0.1700
Data Index: 6946630 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2716. Min Range: -6.2716
Max Act: 5.8028. Min Act: -0.1700
Data Index: 2405563 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2716. Min Range: -6.2716
Max Act: 5.8341. Min Act: -0.1700
Data Index: 7384714 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2716. Min Range: -6.2716
Max Act: 5.8341. Min Act: -0.1700
Data Index: 4143210 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2716. Min Range: -6.2716
Max Act: 5.8341. Min Act: -0.1700
Data Index: 4542409 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2716. Min Range: -6.2716
Max Act: 5.8028. Min Act: -0.1700
Data Index: 7413375 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2716. Min Range: -6.2716
Max Act: 5.8028. Min Act: -0.1700
Data Index: 742881 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2716. Min Range: -6.2716
Max Act: 5.7716. Min Act: -0.1700
Data Index: 2471810 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2716. Min Range: -6.2716
Max Act: 5.7716. Min Act: -0.1700
Data Index: 5936572 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2716. Min Range: -6.2716
Max Act: 5.7716. Min Act: -0.1700
Data Index: 5432514 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2716. Min Range: -6.2716
Max Act: 5.8028. Min Act: -0.1700
Data Index: 1326799 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2716. Min Range: -6.2716
Max Act: 5.8028. Min Act: -0.1700
Data Index: 4356119 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19