Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 689 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2647. Min Range: -4.2647
Max Act: 4.2647. Min Act: -0.1700
Data Index: 8482100 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.8896. Min Act: -0.1700
Data Index: 3839508 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.8896. Min Act: -0.1700
Data Index: 3138444 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.8271. Min Act: -0.1700
Data Index: 6428089 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.7958. Min Act: -0.1700
Data Index: 5505857 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.7958. Min Act: -0.1700
Data Index: 4039851 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.7958. Min Act: -0.1700
Data Index: 5204259 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.7645. Min Act: -0.1700
Data Index: 8384695 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.7333. Min Act: -0.1700
Data Index: 8214402 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.7333. Min Act: -0.1700
Data Index: 3268958 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.7333. Min Act: -0.1700
Data Index: 2365094 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.7333. Min Act: -0.1700
Data Index: 504344 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.7333. Min Act: -0.1700
Data Index: 5236115 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.7333. Min Act: -0.1700
Data Index: 8728135 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.7020. Min Act: -0.1700
Data Index: 3263473 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.6863. Min Act: -0.1700
Data Index: 8391737 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.6863. Min Act: -0.1700
Data Index: 3000234 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.6863. Min Act: -0.1700
Data Index: 8433013 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.6863. Min Act: -0.1700
Data Index: 1402044 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2647. Min Range: -4.2647
Max Act: 3.6707. Min Act: -0.1700
Data Index: 1451273 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19