Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2559 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.3705. Min Act: -0.1700
Data Index: 4900772 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.3391. Min Act: -0.1700
Data Index: 3877396 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.3391. Min Act: -0.1700
Data Index: 671955 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.3077. Min Act: -0.1700
Data Index: 8068981 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.3234. Min Act: -0.1700
Data Index: 2776100 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.2763. Min Act: -0.1700
Data Index: 38607 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.2606. Min Act: -0.1700
Data Index: 2023152 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.2449. Min Act: -0.1700
Data Index: 3876586 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.2449. Min Act: -0.1700
Data Index: 6157655 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.2449. Min Act: -0.1700
Data Index: 4900769 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.2135. Min Act: -0.1700
Data Index: 5845187 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.2135. Min Act: -0.1700
Data Index: 6607770 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.2292. Min Act: -0.1700
Data Index: 7874540 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.1820. Min Act: -0.1700
Data Index: 6547766 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.1820. Min Act: -0.1700
Data Index: 3259874 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.1978. Min Act: -0.1700
Data Index: 5630687 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.1978. Min Act: -0.1700
Data Index: 4243568 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.1663. Min Act: -0.1700
Data Index: 2009199 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.1820. Min Act: -0.1700
Data Index: 3097405 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3705. Min Range: -3.3705
Max Act: 3.1820. Min Act: -0.1700
Data Index: 7490862 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19