Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1806 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.5716. Min Act: -0.1700
Data Index: 3856009 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.5560. Min Act: -0.1700
Data Index: 3844071 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.5716. Min Act: -0.1700
Data Index: 3203151 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.5403. Min Act: -0.1700
Data Index: 8403566 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.5090. Min Act: -0.1700
Data Index: 6256601 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.5090. Min Act: -0.1700
Data Index: 3844072 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.4933. Min Act: -0.1700
Data Index: 3086535 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.4933. Min Act: -0.1700
Data Index: 6532300 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.4620. Min Act: -0.1700
Data Index: 3752026 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.4620. Min Act: -0.1700
Data Index: 6333618 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.4620. Min Act: -0.1700
Data Index: 3993127 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.4307. Min Act: -0.1700
Data Index: 6082542 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.4620. Min Act: -0.1700
Data Index: 8718433 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.4307. Min Act: -0.1700
Data Index: 3010498 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.3993. Min Act: -0.1700
Data Index: 2950648 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.4150. Min Act: -0.1700
Data Index: 2486509 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.3993. Min Act: -0.1700
Data Index: 6846238 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.3993. Min Act: -0.1700
Data Index: 4232419 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.4150. Min Act: -0.1700
Data Index: 3203152 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5716. Min Range: -3.5716
Max Act: 3.3836. Min Act: -0.1700
Data Index: 6076355 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19