Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2099 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.6712. Min Act: -0.1700
Data Index: 847129 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.6087. Min Act: -0.1700
Data Index: 7763760 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.4212. Min Act: -0.1700
Data Index: 5819311 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.4525. Min Act: -0.1700
Data Index: 4856519 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.4212. Min Act: -0.1700
Data Index: 3374029 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.2650. Min Act: -0.1700
Data Index: 1683753 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.2025. Min Act: -0.1700
Data Index: 7117588 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.2025. Min Act: -0.1700
Data Index: 2542019 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.1712. Min Act: -0.1700
Data Index: 387920 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.2025. Min Act: -0.1700
Data Index: 7687114 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.1400. Min Act: -0.1700
Data Index: 5640270 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.1400. Min Act: -0.1700
Data Index: 6597076 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.1400. Min Act: -0.1700
Data Index: 1646775 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.1400. Min Act: -0.1700
Data Index: 907306 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.0150. Min Act: -0.1700
Data Index: 260227 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.0462. Min Act: -0.1700
Data Index: 212904 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.0462. Min Act: -0.1700
Data Index: 3884816 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.0150. Min Act: -0.1700
Data Index: 1081141 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.0150. Min Act: -0.1700
Data Index: 5640285 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.0150. Min Act: -0.1700
Data Index: 3732255 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19