Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1784 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.7767. Min Act: -0.1700
Data Index: 8212473 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.7142. Min Act: -0.1700
Data Index: 1276004 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.6829. Min Act: -0.1700
Data Index: 6227138 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.4954. Min Act: -0.1700
Data Index: 3985394 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.4642. Min Act: -0.1700
Data Index: 1450307 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.4329. Min Act: -0.1700
Data Index: 6257118 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.4329. Min Act: -0.1700
Data Index: 171281 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.4017. Min Act: -0.1700
Data Index: 7606129 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.4017. Min Act: -0.1700
Data Index: 5341955 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.3704. Min Act: -0.1700
Data Index: 996901 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.3704. Min Act: -0.1700
Data Index: 4578623 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.3392. Min Act: -0.1700
Data Index: 646541 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.3392. Min Act: -0.1700
Data Index: 8462843 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.2454. Min Act: -0.1700
Data Index: 8122189 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.2767. Min Act: -0.1700
Data Index: 5100612 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.2454. Min Act: -0.1700
Data Index: 4906264 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.1829. Min Act: -0.1700
Data Index: 2168167 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.2142. Min Act: -0.1700
Data Index: 2654191 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.1829. Min Act: -0.1700
Data Index: 310355 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7767. Min Range: -7.7767
Max Act: 7.2142. Min Act: -0.1700
Data Index: 7847857 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19