Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1344 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0213. Min Range: -3.0213
Max Act: 3.0213. Min Act: -0.1700
Data Index: 995131 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.9264. Min Act: -0.1700
Data Index: 887743 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.9105. Min Act: -0.1700
Data Index: 1032189 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.8629. Min Act: -0.1700
Data Index: 7516404 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.8629. Min Act: -0.1700
Data Index: 6397825 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.8629. Min Act: -0.1700
Data Index: 5860311 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.8470. Min Act: -0.1700
Data Index: 2241246 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.8470. Min Act: -0.1700
Data Index: 33861 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.8470. Min Act: -0.1700
Data Index: 2094822 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.8152. Min Act: -0.1700
Data Index: 2650542 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.8152. Min Act: -0.1700
Data Index: 3937393 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.8152. Min Act: -0.1700
Data Index: 7276983 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.8152. Min Act: -0.1700
Data Index: 4510252 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.8152. Min Act: -0.1700
Data Index: 8244574 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.7993. Min Act: -0.1700
Data Index: 4784976 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.7993. Min Act: -0.1700
Data Index: 156753 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.7993. Min Act: -0.1700
Data Index: 2204481 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.7993. Min Act: -0.1700
Data Index: 2537944 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.7834. Min Act: -0.1700
Data Index: 5510044 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0213. Min Range: -3.0213
Max Act: 2.7834. Min Act: -0.1700
Data Index: 1174531 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19