Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1930 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2853. Min Act: -0.1700
Data Index: 6620656 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2853. Min Act: -0.1700
Data Index: 5971694 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2696. Min Act: -0.1700
Data Index: 4201993 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.2382. Min Act: -0.1700
Data Index: 2519167 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.1438. Min Act: -0.1700
Data Index: 847545 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.1438. Min Act: -0.1700
Data Index: 2580811 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.0650. Min Act: -0.1700
Data Index: 7027787 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.0808. Min Act: -0.1700
Data Index: 5763532 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.0492. Min Act: -0.1700
Data Index: 5940404 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.0334. Min Act: -0.1700
Data Index: 8684992 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.0018. Min Act: -0.1700
Data Index: 503336 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2853. Min Range: -3.2853
Max Act: 3.0176. Min Act: -0.1700
Data Index: 4659279 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2853. Min Range: -3.2853
Max Act: 2.9860. Min Act: -0.1700
Data Index: 1266450 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2853. Min Range: -3.2853
Max Act: 2.9860. Min Act: -0.1700
Data Index: 217664 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2853. Min Range: -3.2853
Max Act: 2.9544. Min Act: -0.1700
Data Index: 8453973 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2853. Min Range: -3.2853
Max Act: 2.9544. Min Act: -0.1700
Data Index: 3306916 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2853. Min Range: -3.2853
Max Act: 2.9702. Min Act: -0.1700
Data Index: 4718693 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2853. Min Range: -3.2853
Max Act: 2.9544. Min Act: -0.1700
Data Index: 7756030 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2853. Min Range: -3.2853
Max Act: 2.9544. Min Act: -0.1700
Data Index: 4172630 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2853. Min Range: -3.2853
Max Act: 2.9386. Min Act: -0.1700
Data Index: 6219041 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19