Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2147 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.9012. Min Act: -0.1700
Data Index: 1291480 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.9324. Min Act: -0.1700
Data Index: 5475417 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.9012. Min Act: -0.1700
Data Index: 6647681 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.8699. Min Act: -0.1700
Data Index: 704636 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.8387. Min Act: -0.1700
Data Index: 6404918 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.8387. Min Act: -0.1700
Data Index: 2624581 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.8387. Min Act: -0.1700
Data Index: 7068652 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.8387. Min Act: -0.1700
Data Index: 6316203 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.8074. Min Act: -0.1700
Data Index: 5421934 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.8074. Min Act: -0.1700
Data Index: 1632473 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.7762. Min Act: -0.1700
Data Index: 3794208 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.7762. Min Act: -0.1700
Data Index: 6582995 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.7762. Min Act: -0.1700
Data Index: 3998237 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.7762. Min Act: -0.1700
Data Index: 2775824 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.7449. Min Act: -0.1700
Data Index: 2931600 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.7449. Min Act: -0.1700
Data Index: 478949 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.7137. Min Act: -0.1700
Data Index: 3960328 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.7137. Min Act: -0.1700
Data Index: 7726074 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.7137. Min Act: -0.1700
Data Index: 706626 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9324. Min Range: -5.9324
Max Act: 5.6824. Min Act: -0.1700
Data Index: 2732268 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19