Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2020 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6375. Min Range: -6.6375
Max Act: 6.6375. Min Act: -0.1700
Data Index: 1724327 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6375. Min Range: -6.6375
Max Act: 6.2938. Min Act: -0.1700
Data Index: 7545187 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6375. Min Range: -6.6375
Max Act: 6.2000. Min Act: -0.1700
Data Index: 6460113 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6375. Min Range: -6.6375
Max Act: 6.1688. Min Act: -0.1700
Data Index: 8334139 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6375. Min Range: -6.6375
Max Act: 6.1063. Min Act: -0.1700
Data Index: 3178601 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6375. Min Range: -6.6375
Max Act: 6.0438. Min Act: -0.1700
Data Index: 7369462 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6375. Min Range: -6.6375
Max Act: 6.0750. Min Act: -0.1700
Data Index: 1153365 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6375. Min Range: -6.6375
Max Act: 6.0125. Min Act: -0.1700
Data Index: 1625116 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6375. Min Range: -6.6375
Max Act: 6.0125. Min Act: -0.1700
Data Index: 3202678 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6375. Min Range: -6.6375
Max Act: 6.0125. Min Act: -0.1700
Data Index: 6779112 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6375. Min Range: -6.6375
Max Act: 5.9813. Min Act: -0.1700
Data Index: 3470528 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6375. Min Range: -6.6375
Max Act: 5.9500. Min Act: -0.1700
Data Index: 7845379 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6375. Min Range: -6.6375
Max Act: 5.9500. Min Act: -0.1700
Data Index: 1414969 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6375. Min Range: -6.6375
Max Act: 5.8875. Min Act: -0.1700
Data Index: 8396650 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6375. Min Range: -6.6375
Max Act: 5.8875. Min Act: -0.1700
Data Index: 3038851 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6375. Min Range: -6.6375
Max Act: 5.8563. Min Act: -0.1700
Data Index: 2458864 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6375. Min Range: -6.6375
Max Act: 5.8875. Min Act: -0.1700
Data Index: 5530815 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6375. Min Range: -6.6375
Max Act: 5.8563. Min Act: -0.1700
Data Index: 5328594 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6375. Min Range: -6.6375
Max Act: 5.8250. Min Act: -0.1700
Data Index: 8153046 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6375. Min Range: -6.6375
Max Act: 5.8875. Min Act: -0.1700
Data Index: 1342192 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19