Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.6164. Min Act: -0.1700
Data Index: 2253034 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.6164. Min Act: -0.1700
Data Index: 4462593 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.5539. Min Act: -0.1700
Data Index: 5398559 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.4914. Min Act: -0.1700
Data Index: 553529 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.4601. Min Act: -0.1700
Data Index: 6090315 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.4914. Min Act: -0.1700
Data Index: 885150 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.4289. Min Act: -0.1700
Data Index: 6063209 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.4289. Min Act: -0.1700
Data Index: 1705849 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3976. Min Act: -0.1700
Data Index: 3171309 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3976. Min Act: -0.1700
Data Index: 8559091 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3976. Min Act: -0.1700
Data Index: 1387080 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3976. Min Act: -0.1700
Data Index: 3295452 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3976. Min Act: -0.1700
Data Index: 1068442 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3976. Min Act: -0.1700
Data Index: 4349299 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3976. Min Act: -0.1700
Data Index: 6370567 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3351. Min Act: -0.1700
Data Index: 6435993 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3351. Min Act: -0.1700
Data Index: 3851880 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3351. Min Act: -0.1700
Data Index: 4337264 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3039. Min Act: -0.1700
Data Index: 651070 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3039. Min Act: -0.1700
Data Index: 6405199 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19