Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4608 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.9259. Min Act: -0.1700
Data Index: 7717631 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.9259. Min Act: -0.1700
Data Index: 8483720 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.8634. Min Act: -0.1700
Data Index: 2551256 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.8321. Min Act: -0.1700
Data Index: 4403511 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.8634. Min Act: -0.1700
Data Index: 3253137 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.8321. Min Act: -0.1700
Data Index: 2540112 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.8009. Min Act: -0.1700
Data Index: 7636249 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.8009. Min Act: -0.1700
Data Index: 7661 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.8009. Min Act: -0.1700
Data Index: 6252344 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.8009. Min Act: -0.1700
Data Index: 2936034 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.8009. Min Act: -0.1700
Data Index: 2257008 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7696. Min Act: -0.1700
Data Index: 707550 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7696. Min Act: -0.1700
Data Index: 1046251 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7696. Min Act: -0.1700
Data Index: 2579180 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7384. Min Act: -0.1700
Data Index: 4994178 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7384. Min Act: -0.1700
Data Index: 6964056 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7384. Min Act: -0.1700
Data Index: 1620335 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7384. Min Act: -0.1700
Data Index: 8178843 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7071. Min Act: -0.1700
Data Index: 3415007 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9259. Min Range: -4.9259
Max Act: 4.7071. Min Act: -0.1700
Data Index: 4093065 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19