Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4370 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6067. Min Range: -9.6067
Max Act: 9.6067. Min Act: -0.1700
Data Index: 1411155 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.9817. Min Act: -0.1700
Data Index: 23378 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.8567. Min Act: -0.1700
Data Index: 348126 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.9192. Min Act: -0.1700
Data Index: 1043817 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.8567. Min Act: -0.1700
Data Index: 5039536 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.8567. Min Act: -0.1700
Data Index: 6208888 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.7942. Min Act: -0.1700
Data Index: 2271805 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.7317. Min Act: -0.1700
Data Index: 4911289 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.7317. Min Act: -0.1700
Data Index: 6138433 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.7317. Min Act: -0.1700
Data Index: 3874042 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.7317. Min Act: -0.1700
Data Index: 1421082 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.6692. Min Act: -0.1700
Data Index: 8721243 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.6692. Min Act: -0.1700
Data Index: 5515988 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.6067. Min Act: -0.1700
Data Index: 7365937 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.6067. Min Act: -0.1700
Data Index: 1760815 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.5442. Min Act: -0.1700
Data Index: 694841 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.4817. Min Act: -0.1700
Data Index: 3067578 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.4817. Min Act: -0.1700
Data Index: 8618898 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.4817. Min Act: -0.1700
Data Index: 2726158 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6067. Min Range: -9.6067
Max Act: 8.4192. Min Act: -0.1700
Data Index: 4181404 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19