Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4092 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2615. Min Range: -6.2615
Max Act: 6.2615. Min Act: -0.1700
Data Index: 3811095 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2615. Min Range: -6.2615
Max Act: 6.0740. Min Act: -0.1700
Data Index: 2987366 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2615. Min Range: -6.2615
Max Act: 6.0428. Min Act: -0.1700
Data Index: 684320 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.9490. Min Act: -0.1700
Data Index: 1701396 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.8553. Min Act: -0.1700
Data Index: 1324846 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.8865. Min Act: -0.1700
Data Index: 5202790 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.8240. Min Act: -0.1700
Data Index: 7173955 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.7615. Min Act: -0.1700
Data Index: 3674618 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.7303. Min Act: -0.1700
Data Index: 6321110 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.7303. Min Act: -0.1700
Data Index: 7088764 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.6990. Min Act: -0.1700
Data Index: 8167511 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.6678. Min Act: -0.1700
Data Index: 5169065 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.6678. Min Act: -0.1700
Data Index: 460526 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.6678. Min Act: -0.1700
Data Index: 8484154 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.6365. Min Act: -0.1700
Data Index: 558089 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.6053. Min Act: -0.1700
Data Index: 2767112 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.6053. Min Act: -0.1700
Data Index: 7435162 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.5740. Min Act: -0.1700
Data Index: 8011851 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.5428. Min Act: -0.1700
Data Index: 5034256 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.5740. Min Act: -0.1700
Data Index: 5713450 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19