Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 112 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0886. Min Range: -7.0886
Max Act: 7.0886. Min Act: -0.1700
Data Index: 6700339 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.4948. Min Act: -0.1700
Data Index: 5254681 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.5261. Min Act: -0.1700
Data Index: 3953310 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.3386. Min Act: -0.1700
Data Index: 7711280 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.3073. Min Act: -0.1700
Data Index: 3255559 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.2761. Min Act: -0.1700
Data Index: 1109076 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.2136. Min Act: -0.1700
Data Index: 5621356 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.1823. Min Act: -0.1700
Data Index: 1876917 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.1511. Min Act: -0.1700
Data Index: 6810321 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.1511. Min Act: -0.1700
Data Index: 2335082 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.0886. Min Act: -0.1700
Data Index: 8696270 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.0886. Min Act: -0.1700
Data Index: 1660934 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.0886. Min Act: -0.1700
Data Index: 3276059 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.0573. Min Act: -0.1700
Data Index: 428205 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.1198. Min Act: -0.1700
Data Index: 4220986 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.0261. Min Act: -0.1700
Data Index: 7696580 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.0573. Min Act: -0.1700
Data Index: 1476993 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0886. Min Range: -7.0886
Max Act: 5.9948. Min Act: -0.1700
Data Index: 1718852 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0886. Min Range: -7.0886
Max Act: 5.9948. Min Act: -0.1700
Data Index: 7969384 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0886. Min Range: -7.0886
Max Act: 6.0573. Min Act: -0.1700
Data Index: 784393 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19