Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 386 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.3523. Min Act: -0.1700
Data Index: 2316885 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2586. Min Act: -0.1700
Data Index: 4989376 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2586. Min Act: -0.1700
Data Index: 5208320 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.1648. Min Act: -0.1700
Data Index: 5918513 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.1335. Min Act: -0.1700
Data Index: 8509787 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.0710. Min Act: -0.1700
Data Index: 6401338 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.0710. Min Act: -0.1700
Data Index: 2673294 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.0085. Min Act: -0.1700
Data Index: 5024413 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3523. Min Range: -4.3523
Max Act: 3.9460. Min Act: -0.1700
Data Index: 6455376 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3523. Min Range: -4.3523
Max Act: 3.9772. Min Act: -0.1700
Data Index: 1838199 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3523. Min Range: -4.3523
Max Act: 3.9772. Min Act: -0.1700
Data Index: 4811871 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3523. Min Range: -4.3523
Max Act: 3.9460. Min Act: -0.1700
Data Index: 542623 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3523. Min Range: -4.3523
Max Act: 3.8835. Min Act: -0.1700
Data Index: 3938434 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3523. Min Range: -4.3523
Max Act: 3.9147. Min Act: -0.1700
Data Index: 1874760 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3523. Min Range: -4.3523
Max Act: 3.8835. Min Act: -0.1700
Data Index: 3462743 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3523. Min Range: -4.3523
Max Act: 3.8835. Min Act: -0.1700
Data Index: 2036682 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3523. Min Range: -4.3523
Max Act: 3.8835. Min Act: -0.1700
Data Index: 897584 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3523. Min Range: -4.3523
Max Act: 3.8522. Min Act: -0.1700
Data Index: 6375161 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3523. Min Range: -4.3523
Max Act: 3.8522. Min Act: -0.1700
Data Index: 989653 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3523. Min Range: -4.3523
Max Act: 3.8522. Min Act: -0.1700
Data Index: 5434123 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19