Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 809 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2994. Min Range: -4.2994
Max Act: 4.2994. Min Act: -0.1700
Data Index: 4955388 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.9556. Min Act: -0.1700
Data Index: 2279215 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.9556. Min Act: -0.1700
Data Index: 5921460 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.9243. Min Act: -0.1700
Data Index: 5120355 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.8931. Min Act: -0.1700
Data Index: 2778414 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.8305. Min Act: -0.1700
Data Index: 3988182 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.8305. Min Act: -0.1700
Data Index: 5271337 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.8618. Min Act: -0.1700
Data Index: 6664949 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.7992. Min Act: -0.1700
Data Index: 7260954 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.7836. Min Act: -0.1700
Data Index: 738866 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.8305. Min Act: -0.1700
Data Index: 320479 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.7523. Min Act: -0.1700
Data Index: 2942723 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.7992. Min Act: -0.1700
Data Index: 6100530 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.7367. Min Act: -0.1700
Data Index: 4578848 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.7210. Min Act: -0.1700
Data Index: 3596037 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.7367. Min Act: -0.1700
Data Index: 2235000 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.7367. Min Act: -0.1700
Data Index: 3636433 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.7367. Min Act: -0.1700
Data Index: 8088602 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.7992. Min Act: -0.1700
Data Index: 949502 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2994. Min Range: -4.2994
Max Act: 3.7054. Min Act: -0.1700
Data Index: 1055451 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19