Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2554 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.7724. Min Act: -0.1700
Data Index: 3970 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.5537. Min Act: -0.1700
Data Index: 2407227 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.4912. Min Act: -0.1700
Data Index: 4624128 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.4912. Min Act: -0.1700
Data Index: 7582779 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.4912. Min Act: -0.1700
Data Index: 724033 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.4599. Min Act: -0.1700
Data Index: 6112334 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.4287. Min Act: -0.1700
Data Index: 8390317 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.3974. Min Act: -0.1700
Data Index: 2103602 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.3974. Min Act: -0.1700
Data Index: 2873697 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.3662. Min Act: -0.1700
Data Index: 7873459 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.3662. Min Act: -0.1700
Data Index: 2127405 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.3349. Min Act: -0.1700
Data Index: 6745363 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.3349. Min Act: -0.1700
Data Index: 6448415 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.3349. Min Act: -0.1700
Data Index: 5259316 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.3037. Min Act: -0.1700
Data Index: 5825787 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.3037. Min Act: -0.1700
Data Index: 8586711 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.3349. Min Act: -0.1700
Data Index: 7509087 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.2724. Min Act: -0.1700
Data Index: 7567633 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.3037. Min Act: -0.1700
Data Index: 4830657 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7724. Min Range: -4.7724
Max Act: 4.2724. Min Act: -0.1700
Data Index: 5949071 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19