Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3668 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5321. Min Range: -4.5321
Max Act: 4.5321. Min Act: -0.1700
Data Index: 3738212 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5321. Min Range: -4.5321
Max Act: 4.3133. Min Act: -0.1700
Data Index: 2142430 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5321. Min Range: -4.5321
Max Act: 4.2508. Min Act: -0.1700
Data Index: 8183793 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5321. Min Range: -4.5321
Max Act: 4.0633. Min Act: -0.1700
Data Index: 2947358 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5321. Min Range: -4.5321
Max Act: 4.0946. Min Act: -0.1700
Data Index: 7163453 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5321. Min Range: -4.5321
Max Act: 4.0320. Min Act: -0.1700
Data Index: 2309254 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5321. Min Range: -4.5321
Max Act: 4.0320. Min Act: -0.1700
Data Index: 3533506 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5321. Min Range: -4.5321
Max Act: 4.0008. Min Act: -0.1700
Data Index: 887566 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5321. Min Range: -4.5321
Max Act: 4.0008. Min Act: -0.1700
Data Index: 6336227 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5321. Min Range: -4.5321
Max Act: 3.9695. Min Act: -0.1700
Data Index: 3574840 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5321. Min Range: -4.5321
Max Act: 3.9070. Min Act: -0.1700
Data Index: 625709 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5321. Min Range: -4.5321
Max Act: 3.9070. Min Act: -0.1700
Data Index: 5948104 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5321. Min Range: -4.5321
Max Act: 3.9070. Min Act: -0.1700
Data Index: 3834350 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5321. Min Range: -4.5321
Max Act: 3.9070. Min Act: -0.1700
Data Index: 7442641 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5321. Min Range: -4.5321
Max Act: 3.9070. Min Act: -0.1700
Data Index: 8661010 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5321. Min Range: -4.5321
Max Act: 3.9070. Min Act: -0.1700
Data Index: 4166409 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5321. Min Range: -4.5321
Max Act: 3.9070. Min Act: -0.1700
Data Index: 4531945 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5321. Min Range: -4.5321
Max Act: 3.8757. Min Act: -0.1700
Data Index: 6335102 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5321. Min Range: -4.5321
Max Act: 3.8445. Min Act: -0.1700
Data Index: 2321670 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5321. Min Range: -4.5321
Max Act: 3.8445. Min Act: -0.1700
Data Index: 1612909 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19