Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5463 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0371. Min Range: -6.0371
Max Act: 6.0058. Min Act: -0.1699
Data Index: 3325056 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0371. Min Range: -6.0371
Max Act: 6.0371. Min Act: -0.1700
Data Index: 1586789 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0371. Min Range: -6.0371
Max Act: 6.0371. Min Act: -0.1700
Data Index: 8216884 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0371. Min Range: -6.0371
Max Act: 6.0371. Min Act: -0.1699
Data Index: 3261674 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0371. Min Range: -6.0371
Max Act: 5.9746. Min Act: -0.1699
Data Index: 4047495 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0371. Min Range: -6.0371
Max Act: 6.0058. Min Act: -0.1700
Data Index: 1845391 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0371. Min Range: -6.0371
Max Act: 6.0058. Min Act: -0.1700
Data Index: 2376651 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0371. Min Range: -6.0371
Max Act: 6.0058. Min Act: -0.1699
Data Index: 6331183 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0371. Min Range: -6.0371
Max Act: 6.0058. Min Act: -0.1700
Data Index: 5718651 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0371. Min Range: -6.0371
Max Act: 5.9746. Min Act: -0.1700
Data Index: 2417603 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0371. Min Range: -6.0371
Max Act: 5.9746. Min Act: -0.1700
Data Index: 6856126 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0371. Min Range: -6.0371
Max Act: 5.9746. Min Act: -0.1700
Data Index: 65242 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0371. Min Range: -6.0371
Max Act: 5.9746. Min Act: -0.1700
Data Index: 1077427 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0371. Min Range: -6.0371
Max Act: 5.9746. Min Act: -0.1700
Data Index: 2181496 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0371. Min Range: -6.0371
Max Act: 5.9746. Min Act: -0.1700
Data Index: 5676709 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0371. Min Range: -6.0371
Max Act: 5.9746. Min Act: -0.1700
Data Index: 2872979 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0371. Min Range: -6.0371
Max Act: 5.9746. Min Act: -0.1700
Data Index: 4184983 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0371. Min Range: -6.0371
Max Act: 5.9746. Min Act: -0.1700
Data Index: 895007 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0371. Min Range: -6.0371
Max Act: 5.9433. Min Act: -0.1700
Data Index: 2278126 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0371. Min Range: -6.0371
Max Act: 5.9746. Min Act: -0.1700
Data Index: 3290108 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19