Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2057 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.5210. Min Act: -0.1700
Data Index: 912982 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.5210. Min Act: -0.1700
Data Index: 4181012 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.3960. Min Act: -0.1700
Data Index: 1793185 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.3648. Min Act: -0.1700
Data Index: 2048950 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.3960. Min Act: -0.1700
Data Index: 8007077 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.3960. Min Act: -0.1700
Data Index: 739029 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.3648. Min Act: -0.1700
Data Index: 995053 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.3335. Min Act: -0.1700
Data Index: 3788696 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.3023. Min Act: -0.1700
Data Index: 6103811 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.3023. Min Act: -0.1700
Data Index: 2968718 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.2710. Min Act: -0.1700
Data Index: 995054 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.3023. Min Act: -0.1700
Data Index: 4866116 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.2398. Min Act: -0.1700
Data Index: 3792858 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.2398. Min Act: -0.1700
Data Index: 8378462 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.2710. Min Act: -0.1700
Data Index: 1505368 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.2085. Min Act: -0.1700
Data Index: 1427009 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.2085. Min Act: -0.1700
Data Index: 7294975 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.1460. Min Act: -0.1700
Data Index: 7106273 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.1773. Min Act: -0.1700
Data Index: 2635488 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5210. Min Range: -5.5210
Max Act: 5.1773. Min Act: -0.1700
Data Index: 47268 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19