Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2096 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.2838. Min Act: -0.1700
Data Index: 5095051 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.2838. Min Act: -0.1700
Data Index: 4875866 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.1900. Min Act: -0.1700
Data Index: 6999295 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.1588. Min Act: -0.1700
Data Index: 3874119 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.1900. Min Act: -0.1700
Data Index: 5502413 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.1588. Min Act: -0.1700
Data Index: 6561946 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.1588. Min Act: -0.1700
Data Index: 891690 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.1275. Min Act: -0.1700
Data Index: 1240018 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.0650. Min Act: -0.1700
Data Index: 2964723 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.0963. Min Act: -0.1700
Data Index: 7616254 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.0963. Min Act: -0.1700
Data Index: 2777603 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.0963. Min Act: -0.1700
Data Index: 1173495 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.0650. Min Act: -0.1700
Data Index: 1981027 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.0650. Min Act: -0.1700
Data Index: 1531181 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.0025. Min Act: -0.1700
Data Index: 6472021 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.0025. Min Act: -0.1700
Data Index: 2469428 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2838. Min Range: -5.2838
Max Act: 4.9713. Min Act: -0.1700
Data Index: 4940047 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.0025. Min Act: -0.1700
Data Index: 480020 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.0025. Min Act: -0.1700
Data Index: 2111664 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2838. Min Range: -5.2838
Max Act: 5.0025. Min Act: -0.1700
Data Index: 855859 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19