Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1219 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6427. Min Range: -8.6427
Max Act: 8.6427. Min Act: -0.1700
Data Index: 2310839 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6427. Min Range: -8.6427
Max Act: 8.6427. Min Act: -0.1700
Data Index: 2107533 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6427. Min Range: -8.6427
Max Act: 8.3302. Min Act: -0.1700
Data Index: 2801677 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6427. Min Range: -8.6427
Max Act: 8.2052. Min Act: -0.1700
Data Index: 8047564 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6427. Min Range: -8.6427
Max Act: 8.2052. Min Act: -0.1700
Data Index: 6522192 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6427. Min Range: -8.6427
Max Act: 8.0802. Min Act: -0.1700
Data Index: 6632684 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6427. Min Range: -8.6427
Max Act: 8.1427. Min Act: -0.1700
Data Index: 4162509 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6427. Min Range: -8.6427
Max Act: 7.7677. Min Act: -0.1700
Data Index: 530471 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6427. Min Range: -8.6427
Max Act: 7.7677. Min Act: -0.1700
Data Index: 3867363 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6427. Min Range: -8.6427
Max Act: 7.7052. Min Act: -0.1700
Data Index: 1118755 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6427. Min Range: -8.6427
Max Act: 7.7677. Min Act: -0.1700
Data Index: 4724962 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6427. Min Range: -8.6427
Max Act: 7.7677. Min Act: -0.1700
Data Index: 47319 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6427. Min Range: -8.6427
Max Act: 7.5802. Min Act: -0.1700
Data Index: 2597339 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6427. Min Range: -8.6427
Max Act: 7.6427. Min Act: -0.1700
Data Index: 4600171 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6427. Min Range: -8.6427
Max Act: 7.6427. Min Act: -0.1700
Data Index: 4784849 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6427. Min Range: -8.6427
Max Act: 7.6427. Min Act: -0.1700
Data Index: 8431137 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6427. Min Range: -8.6427
Max Act: 7.7052. Min Act: -0.1700
Data Index: 7580865 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6427. Min Range: -8.6427
Max Act: 7.6427. Min Act: -0.1700
Data Index: 1512338 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6427. Min Range: -8.6427
Max Act: 7.5802. Min Act: -0.1700
Data Index: 1655749 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6427. Min Range: -8.6427
Max Act: 7.5802. Min Act: -0.1700
Data Index: 7568256 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19