Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1799 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.8477. Min Act: -0.1700
Data Index: 2017043 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.8321. Min Act: -0.1700
Data Index: 4264419 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.7852. Min Act: -0.1700
Data Index: 2144929 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.7383. Min Act: -0.1700
Data Index: 6204161 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.7383. Min Act: -0.1700
Data Index: 8687579 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.7226. Min Act: -0.1700
Data Index: 6748724 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.7070. Min Act: -0.1700
Data Index: 4486688 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.6601. Min Act: -0.1700
Data Index: 7399892 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.6444. Min Act: -0.1700
Data Index: 296369 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.6288. Min Act: -0.1700
Data Index: 1193792 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.6131. Min Act: -0.1700
Data Index: 8387519 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.6131. Min Act: -0.1700
Data Index: 2525489 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.6131. Min Act: -0.1700
Data Index: 8525835 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.6131. Min Act: -0.1700
Data Index: 4741587 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.5975. Min Act: -0.1700
Data Index: 3805791 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.5975. Min Act: -0.1700
Data Index: 1712684 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.5818. Min Act: -0.1700
Data Index: 5447036 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.5818. Min Act: -0.1700
Data Index: 3594503 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.5975. Min Act: -0.1700
Data Index: 8163762 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8477. Min Range: -3.8477
Max Act: 3.5818. Min Act: -0.1700
Data Index: 5913530 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19