Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.4033. Min Act: -0.1700
Data Index: 7251027 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.2471. Min Act: -0.1700
Data Index: 7975468 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.2471. Min Act: -0.1700
Data Index: 5711973 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.2471. Min Act: -0.1700
Data Index: 7459400 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.2158. Min Act: -0.1700
Data Index: 3610189 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.2158. Min Act: -0.1700
Data Index: 5453931 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.2158. Min Act: -0.1700
Data Index: 7193815 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.1846. Min Act: -0.1700
Data Index: 128329 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.1846. Min Act: -0.1700
Data Index: 6270247 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.1533. Min Act: -0.1700
Data Index: 6731477 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.1533. Min Act: -0.1700
Data Index: 4865703 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.1846. Min Act: -0.1700
Data Index: 5270447 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.1221. Min Act: -0.1700
Data Index: 5508300 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.1533. Min Act: -0.1700
Data Index: 7344704 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.1533. Min Act: -0.1700
Data Index: 3508615 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.1533. Min Act: -0.1700
Data Index: 1218509 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.1533. Min Act: -0.1700
Data Index: 4417453 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.1533. Min Act: -0.1700
Data Index: 2765017 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.1533. Min Act: -0.1700
Data Index: 3866079 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4033. Min Range: -6.4033
Max Act: 6.1533. Min Act: -0.1700
Data Index: 234746 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19