Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2824 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.8150. Min Act: -0.1700
Data Index: 8257054 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.7212. Min Act: -0.1700
Data Index: 3866923 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.6900. Min Act: -0.1700
Data Index: 3028397 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.6900. Min Act: -0.1700
Data Index: 8311365 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.6587. Min Act: -0.1700
Data Index: 7059430 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.6275. Min Act: -0.1700
Data Index: 7416813 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.6275. Min Act: -0.1700
Data Index: 3919959 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.5650. Min Act: -0.1700
Data Index: 3164520 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.5337. Min Act: -0.1700
Data Index: 1583664 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.5337. Min Act: -0.1700
Data Index: 3724102 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.5025. Min Act: -0.1700
Data Index: 3343494 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.4712. Min Act: -0.1700
Data Index: 8781766 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.5025. Min Act: -0.1700
Data Index: 2402366 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.4712. Min Act: -0.1700
Data Index: 7512029 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.4400. Min Act: -0.1700
Data Index: 471020 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.4087. Min Act: -0.1700
Data Index: 4737771 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.4087. Min Act: -0.1700
Data Index: 870953 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.3775. Min Act: -0.1700
Data Index: 4616354 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.4087. Min Act: -0.1700
Data Index: 2804873 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8150. Min Range: -5.8150
Max Act: 5.3775. Min Act: -0.1700
Data Index: 2505735 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19