Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3342 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.8097. Min Act: -0.1700
Data Index: 580043 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.6847. Min Act: -0.1700
Data Index: 5576845 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.6222. Min Act: -0.1700
Data Index: 954403 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.6222. Min Act: -0.1700
Data Index: 1576497 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.6222. Min Act: -0.1700
Data Index: 3833304 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.5597. Min Act: -0.1700
Data Index: 4810136 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.5597. Min Act: -0.1700
Data Index: 6721576 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.5597. Min Act: -0.1700
Data Index: 7823827 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.4972. Min Act: -0.1700
Data Index: 5776535 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.4972. Min Act: -0.1700
Data Index: 2479373 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.4972. Min Act: -0.1700
Data Index: 6994544 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.4972. Min Act: -0.1700
Data Index: 8824360 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.4347. Min Act: -0.1700
Data Index: 5220294 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.4347. Min Act: -0.1700
Data Index: 8104591 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.4347. Min Act: -0.1700
Data Index: 7153771 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.4347. Min Act: -0.1700
Data Index: 6898774 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.4347. Min Act: -0.1700
Data Index: 2599149 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.4347. Min Act: -0.1700
Data Index: 8691750 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.3722. Min Act: -0.1700
Data Index: 3197347 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8097. Min Range: -9.8097
Max Act: 9.3722. Min Act: -0.1700
Data Index: 8414450 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19