Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2786 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.4972. Min Act: -0.1700
Data Index: 974976 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.4659. Min Act: -0.1700
Data Index: 1238922 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.4034. Min Act: -0.1700
Data Index: 1582827 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.4034. Min Act: -0.1700
Data Index: 1389361 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.3722. Min Act: -0.1700
Data Index: 1927166 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.3097. Min Act: -0.1700
Data Index: 1249794 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.3097. Min Act: -0.1700
Data Index: 5544610 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.2472. Min Act: -0.1700
Data Index: 4873931 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.2159. Min Act: -0.1700
Data Index: 5547069 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.2159. Min Act: -0.1700
Data Index: 3075425 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.1846. Min Act: -0.1700
Data Index: 889165 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.1534. Min Act: -0.1700
Data Index: 1025503 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.1534. Min Act: -0.1700
Data Index: 5859935 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.1846. Min Act: -0.1700
Data Index: 2077022 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.1534. Min Act: -0.1700
Data Index: 8074625 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.1534. Min Act: -0.1700
Data Index: 291945 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.1221. Min Act: -0.1700
Data Index: 5663122 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.1221. Min Act: -0.1700
Data Index: 6041457 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.0909. Min Act: -0.1700
Data Index: 300663 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4972. Min Range: -4.4972
Max Act: 4.0596. Min Act: -0.1700
Data Index: 1390993 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19