Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3332 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.5703. Min Act: -0.1700
Data Index: 689028 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.5391. Min Act: -0.1700
Data Index: 677024 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.5078. Min Act: -0.1700
Data Index: 1581444 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.5078. Min Act: -0.1700
Data Index: 7192666 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.3516. Min Act: -0.1700
Data Index: 6464735 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.3516. Min Act: -0.1700
Data Index: 5937334 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.2266. Min Act: -0.1700
Data Index: 2786859 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.1953. Min Act: -0.1700
Data Index: 5884211 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.1328. Min Act: -0.1700
Data Index: 1351514 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.1016. Min Act: -0.1700
Data Index: 4444043 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.1016. Min Act: -0.1700
Data Index: 561883 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.0703. Min Act: -0.1700
Data Index: 4412997 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.0391. Min Act: -0.1700
Data Index: 3332383 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.0391. Min Act: -0.1700
Data Index: 4663254 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.0078. Min Act: -0.1700
Data Index: 5950120 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.0391. Min Act: -0.1700
Data Index: 5639177 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.0391. Min Act: -0.1700
Data Index: 6842319 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.0391. Min Act: -0.1700
Data Index: 537177 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.0391. Min Act: -0.1700
Data Index: 4439882 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5703. Min Range: -7.5703
Max Act: 7.0078. Min Act: -0.1700
Data Index: 2320233 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19