Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3447 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.2771. Min Act: -0.1700
Data Index: 5908169 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.2458. Min Act: -0.1700
Data Index: 3703520 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.2458. Min Act: -0.1700
Data Index: 7210609 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.2146. Min Act: -0.1700
Data Index: 1436676 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.2458. Min Act: -0.1700
Data Index: 8692672 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.2146. Min Act: -0.1700
Data Index: 2788195 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.2146. Min Act: -0.1700
Data Index: 929020 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.2146. Min Act: -0.1700
Data Index: 2383297 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.2146. Min Act: -0.1700
Data Index: 5968886 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.2146. Min Act: -0.1700
Data Index: 231825 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.2146. Min Act: -0.1700
Data Index: 8152466 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.2146. Min Act: -0.1700
Data Index: 8100232 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.2146. Min Act: -0.1700
Data Index: 1661344 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.1833. Min Act: -0.1700
Data Index: 1926402 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.1833. Min Act: -0.1700
Data Index: 6550143 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.1833. Min Act: -0.1700
Data Index: 6615803 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.1833. Min Act: -0.1700
Data Index: 1499853 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.1833. Min Act: -0.1700
Data Index: 909832 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.1833. Min Act: -0.1700
Data Index: 1568104 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2771. Min Range: -5.2771
Max Act: 5.1833. Min Act: -0.1700
Data Index: 311088 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19