Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.9730. Min Act: -0.1700
Data Index: 1188839 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.6605. Min Act: -0.1700
Data Index: 2873227 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.4730. Min Act: -0.1700
Data Index: 6795675 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.5043. Min Act: -0.1700
Data Index: 3340740 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.3793. Min Act: -0.1700
Data Index: 1001335 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.3480. Min Act: -0.1700
Data Index: 1974287 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.3168. Min Act: -0.1700
Data Index: 8168765 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.3168. Min Act: -0.1700
Data Index: 8614112 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.2855. Min Act: -0.1700
Data Index: 691369 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.2855. Min Act: -0.1700
Data Index: 8066665 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.2855. Min Act: -0.1700
Data Index: 3492297 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.2543. Min Act: -0.1700
Data Index: 4989883 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.2230. Min Act: -0.1700
Data Index: 7885954 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.2230. Min Act: -0.1700
Data Index: 2552414 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.1605. Min Act: -0.1700
Data Index: 7794737 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.2230. Min Act: -0.1700
Data Index: 7431743 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.1605. Min Act: -0.1700
Data Index: 4208163 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.1605. Min Act: -0.1700
Data Index: 4832627 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.1293. Min Act: -0.1700
Data Index: 3686247 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9730. Min Range: -7.9730
Max Act: 7.0980. Min Act: -0.1700
Data Index: 7402852 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19