Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6024 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.2874. Min Act: -0.1700
Data Index: 7423383 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.2561. Min Act: -0.1700
Data Index: 4531671 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.1623. Min Act: -0.1700
Data Index: 8232616 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.1623. Min Act: -0.1700
Data Index: 5703102 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0998. Min Act: -0.1700
Data Index: 4925419 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0686. Min Act: -0.1700
Data Index: 5652274 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0686. Min Act: -0.1700
Data Index: 4582413 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0373. Min Act: -0.1700
Data Index: 3408570 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0686. Min Act: -0.1700
Data Index: 5759433 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0686. Min Act: -0.1700
Data Index: 1295063 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2874. Min Range: -4.2874
Max Act: 3.9748. Min Act: -0.1700
Data Index: 7171831 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0061. Min Act: -0.1700
Data Index: 2857129 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2874. Min Range: -4.2874
Max Act: 3.9435. Min Act: -0.1700
Data Index: 6059295 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0061. Min Act: -0.1700
Data Index: 7054516 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2874. Min Range: -4.2874
Max Act: 3.9435. Min Act: -0.1700
Data Index: 6738535 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2874. Min Range: -4.2874
Max Act: 3.9435. Min Act: -0.1700
Data Index: 2875424 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2874. Min Range: -4.2874
Max Act: 3.9435. Min Act: -0.1700
Data Index: 5419502 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2874. Min Range: -4.2874
Max Act: 3.9123. Min Act: -0.1700
Data Index: 1467793 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2874. Min Range: -4.2874
Max Act: 3.9123. Min Act: -0.1700
Data Index: 4102845 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2874. Min Range: -4.2874
Max Act: 3.9123. Min Act: -0.1700
Data Index: 6679427 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19