Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1994 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.7420. Min Act: -0.1700
Data Index: 2285531 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.7107. Min Act: -0.1700
Data Index: 3788786 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.4607. Min Act: -0.1700
Data Index: 3711153 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.3982. Min Act: -0.1700
Data Index: 1524104 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.3982. Min Act: -0.1700
Data Index: 8148713 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.3670. Min Act: -0.1700
Data Index: 1457815 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.3357. Min Act: -0.1700
Data Index: 8766440 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.3357. Min Act: -0.1700
Data Index: 2384614 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.3357. Min Act: -0.1700
Data Index: 475253 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.2732. Min Act: -0.1700
Data Index: 530059 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.2732. Min Act: -0.1700
Data Index: 1141941 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.2732. Min Act: -0.1700
Data Index: 2596567 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.2732. Min Act: -0.1700
Data Index: 160731 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.2420. Min Act: -0.1700
Data Index: 3826392 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.2107. Min Act: -0.1700
Data Index: 2935848 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.2107. Min Act: -0.1700
Data Index: 1449509 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.1795. Min Act: -0.1700
Data Index: 7072520 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.2107. Min Act: -0.1700
Data Index: 4334644 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.1795. Min Act: -0.1700
Data Index: 6533273 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7420. Min Range: -5.7420
Max Act: 5.1795. Min Act: -0.1700
Data Index: 5848546 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19