Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3998 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4143. Min Range: -6.4143
Max Act: 6.4143. Min Act: -0.1700
Data Index: 4647305 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4143. Min Range: -6.4143
Max Act: 6.3830. Min Act: -0.1700
Data Index: 2496506 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4143. Min Range: -6.4143
Max Act: 6.1955. Min Act: -0.1700
Data Index: 3429366 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4143. Min Range: -6.4143
Max Act: 6.1018. Min Act: -0.1700
Data Index: 3097933 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4143. Min Range: -6.4143
Max Act: 6.1643. Min Act: -0.1700
Data Index: 4751505 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4143. Min Range: -6.4143
Max Act: 6.1018. Min Act: -0.1700
Data Index: 1028324 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4143. Min Range: -6.4143
Max Act: 6.0705. Min Act: -0.1700
Data Index: 7273308 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4143. Min Range: -6.4143
Max Act: 6.0705. Min Act: -0.1700
Data Index: 5512544 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4143. Min Range: -6.4143
Max Act: 6.0080. Min Act: -0.1700
Data Index: 4943580 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.9768. Min Act: -0.1700
Data Index: 829492 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4143. Min Range: -6.4143
Max Act: 6.0080. Min Act: -0.1700
Data Index: 1220643 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.9455. Min Act: -0.1700
Data Index: 2255662 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.9455. Min Act: -0.1700
Data Index: 829491 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.9143. Min Act: -0.1700
Data Index: 7107094 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.9143. Min Act: -0.1700
Data Index: 1263408 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.9455. Min Act: -0.1700
Data Index: 2453979 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.8830. Min Act: -0.1700
Data Index: 3155181 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.9143. Min Act: -0.1700
Data Index: 4143847 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.8518. Min Act: -0.1700
Data Index: 1942687 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.8205. Min Act: -0.1700
Data Index: 829495 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19