Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4789 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.9255. Min Act: -0.1700
Data Index: 5883777 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.7692. Min Act: -0.1700
Data Index: 3146369 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.7380. Min Act: -0.1700
Data Index: 549560 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.6442. Min Act: -0.1700
Data Index: 4649824 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.4880. Min Act: -0.1700
Data Index: 4074334 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.4255. Min Act: -0.1700
Data Index: 4649816 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.3630. Min Act: -0.1700
Data Index: 2275290 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.3005. Min Act: -0.1700
Data Index: 4413049 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.3005. Min Act: -0.1700
Data Index: 5189806 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.2692. Min Act: -0.1700
Data Index: 673730 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.2692. Min Act: -0.1700
Data Index: 1798437 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.2380. Min Act: -0.1700
Data Index: 5958756 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.3005. Min Act: -0.1700
Data Index: 4139208 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.2692. Min Act: -0.1700
Data Index: 495618 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.2692. Min Act: -0.1700
Data Index: 4704357 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.2380. Min Act: -0.1700
Data Index: 714891 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.2067. Min Act: -0.1700
Data Index: 3119303 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.2067. Min Act: -0.1700
Data Index: 6241146 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.1442. Min Act: -0.1700
Data Index: 217142 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9255. Min Range: -7.9255
Max Act: 7.1755. Min Act: -0.1700
Data Index: 1948853 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19