Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3052 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2731. Min Range: -6.2731
Max Act: 6.2731. Min Act: -0.1700
Data Index: 2168740 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2731. Min Range: -6.2731
Max Act: 6.2106. Min Act: -0.1700
Data Index: 3630334 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2731. Min Range: -6.2731
Max Act: 6.1793. Min Act: -0.1700
Data Index: 3089170 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2731. Min Range: -6.2731
Max Act: 6.0543. Min Act: -0.1700
Data Index: 8559530 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2731. Min Range: -6.2731
Max Act: 5.9918. Min Act: -0.1700
Data Index: 5894062 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2731. Min Range: -6.2731
Max Act: 5.9918. Min Act: -0.1700
Data Index: 2589186 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2731. Min Range: -6.2731
Max Act: 5.9918. Min Act: -0.1700
Data Index: 242090 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2731. Min Range: -6.2731
Max Act: 5.9606. Min Act: -0.1700
Data Index: 339062 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2731. Min Range: -6.2731
Max Act: 5.9293. Min Act: -0.1700
Data Index: 716776 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2731. Min Range: -6.2731
Max Act: 5.8981. Min Act: -0.1700
Data Index: 7549040 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2731. Min Range: -6.2731
Max Act: 5.9293. Min Act: -0.1700
Data Index: 2951770 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2731. Min Range: -6.2731
Max Act: 5.9293. Min Act: -0.1700
Data Index: 1460358 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2731. Min Range: -6.2731
Max Act: 5.8981. Min Act: -0.1700
Data Index: 6773876 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2731. Min Range: -6.2731
Max Act: 5.8981. Min Act: -0.1700
Data Index: 6078680 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2731. Min Range: -6.2731
Max Act: 5.8981. Min Act: -0.1700
Data Index: 6303123 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2731. Min Range: -6.2731
Max Act: 5.8668. Min Act: -0.1700
Data Index: 3296552 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2731. Min Range: -6.2731
Max Act: 5.8356. Min Act: -0.1700
Data Index: 3218584 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2731. Min Range: -6.2731
Max Act: 5.8668. Min Act: -0.1700
Data Index: 3287470 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2731. Min Range: -6.2731
Max Act: 5.8668. Min Act: -0.1700
Data Index: 2135669 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2731. Min Range: -6.2731
Max Act: 5.8668. Min Act: -0.1700
Data Index: 5773444 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19