Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2528 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.6705. Min Act: -0.1700
Data Index: 208697 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.5767. Min Act: -0.1700
Data Index: 5237543 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.5455. Min Act: -0.1700
Data Index: 7904888 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.5455. Min Act: -0.1700
Data Index: 2684828 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.4830. Min Act: -0.1700
Data Index: 7681406 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.5455. Min Act: -0.1700
Data Index: 5586475 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.5142. Min Act: -0.1700
Data Index: 8372171 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.4830. Min Act: -0.1700
Data Index: 2585116 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.4517. Min Act: -0.1700
Data Index: 1827756 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.4517. Min Act: -0.1700
Data Index: 577377 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.4204. Min Act: -0.1700
Data Index: 4438525 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.3892. Min Act: -0.1700
Data Index: 1691464 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.4204. Min Act: -0.1700
Data Index: 8599998 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.4204. Min Act: -0.1700
Data Index: 6457365 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.4517. Min Act: -0.1700
Data Index: 2961665 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.3892. Min Act: -0.1700
Data Index: 3412023 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.4517. Min Act: -0.1700
Data Index: 2935117 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.3892. Min Act: -0.1700
Data Index: 7355334 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.3892. Min Act: -0.1700
Data Index: 7518844 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6705. Min Range: -4.6705
Max Act: 4.3579. Min Act: -0.1700
Data Index: 4268401 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19