Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1992 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3702. Min Range: -6.3702
Max Act: 6.3702. Min Act: -0.1700
Data Index: 3289525 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3702. Min Range: -6.3702
Max Act: 6.2452. Min Act: -0.1700
Data Index: 3995927 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3702. Min Range: -6.3702
Max Act: 6.2452. Min Act: -0.1700
Data Index: 375377 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3702. Min Range: -6.3702
Max Act: 6.2452. Min Act: -0.1700
Data Index: 6371384 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3702. Min Range: -6.3702
Max Act: 6.1515. Min Act: -0.1700
Data Index: 1602276 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3702. Min Range: -6.3702
Max Act: 6.1515. Min Act: -0.1700
Data Index: 3137065 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3702. Min Range: -6.3702
Max Act: 6.0890. Min Act: -0.1700
Data Index: 3728607 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3702. Min Range: -6.3702
Max Act: 6.1202. Min Act: -0.1700
Data Index: 6755840 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3702. Min Range: -6.3702
Max Act: 6.0890. Min Act: -0.1700
Data Index: 4791365 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3702. Min Range: -6.3702
Max Act: 6.0577. Min Act: -0.1700
Data Index: 8492348 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3702. Min Range: -6.3702
Max Act: 6.0577. Min Act: -0.1700
Data Index: 7301656 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3702. Min Range: -6.3702
Max Act: 6.0577. Min Act: -0.1700
Data Index: 6035087 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3702. Min Range: -6.3702
Max Act: 6.0577. Min Act: -0.1700
Data Index: 6465461 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3702. Min Range: -6.3702
Max Act: 5.9952. Min Act: -0.1700
Data Index: 4915472 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3702. Min Range: -6.3702
Max Act: 6.0265. Min Act: -0.1700
Data Index: 449306 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3702. Min Range: -6.3702
Max Act: 5.9640. Min Act: -0.1700
Data Index: 2246980 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3702. Min Range: -6.3702
Max Act: 5.9952. Min Act: -0.1700
Data Index: 1383264 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3702. Min Range: -6.3702
Max Act: 5.9952. Min Act: -0.1700
Data Index: 8331475 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3702. Min Range: -6.3702
Max Act: 5.9952. Min Act: -0.1700
Data Index: 7815808 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3702. Min Range: -6.3702
Max Act: 5.9952. Min Act: -0.1700
Data Index: 418489 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19