Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5913 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3640. Min Range: -6.3640
Max Act: 6.3640. Min Act: -0.1700
Data Index: 8442934 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3640. Min Range: -6.3640
Max Act: 6.2703. Min Act: -0.1700
Data Index: 8360373 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3640. Min Range: -6.3640
Max Act: 6.2390. Min Act: -0.1700
Data Index: 5989057 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3640. Min Range: -6.3640
Max Act: 6.2078. Min Act: -0.1700
Data Index: 7207153 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3640. Min Range: -6.3640
Max Act: 6.1453. Min Act: -0.1700
Data Index: 569914 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3640. Min Range: -6.3640
Max Act: 6.1453. Min Act: -0.1700
Data Index: 3325000 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3640. Min Range: -6.3640
Max Act: 6.0828. Min Act: -0.1700
Data Index: 8395446 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3640. Min Range: -6.3640
Max Act: 6.1140. Min Act: -0.1700
Data Index: 3096994 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3640. Min Range: -6.3640
Max Act: 6.0515. Min Act: -0.1700
Data Index: 8699672 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3640. Min Range: -6.3640
Max Act: 6.0515. Min Act: -0.1700
Data Index: 336713 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3640. Min Range: -6.3640
Max Act: 6.0515. Min Act: -0.1700
Data Index: 1523676 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3640. Min Range: -6.3640
Max Act: 6.0203. Min Act: -0.1700
Data Index: 2575529 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3640. Min Range: -6.3640
Max Act: 6.0515. Min Act: -0.1700
Data Index: 296735 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3640. Min Range: -6.3640
Max Act: 6.0203. Min Act: -0.1700
Data Index: 6787279 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3640. Min Range: -6.3640
Max Act: 6.0203. Min Act: -0.1700
Data Index: 1770142 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3640. Min Range: -6.3640
Max Act: 5.9890. Min Act: -0.1700
Data Index: 7646180 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3640. Min Range: -6.3640
Max Act: 5.9890. Min Act: -0.1700
Data Index: 8464587 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3640. Min Range: -6.3640
Max Act: 5.9890. Min Act: -0.1700
Data Index: 8753165 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3640. Min Range: -6.3640
Max Act: 5.9578. Min Act: -0.1700
Data Index: 8216610 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3640. Min Range: -6.3640
Max Act: 5.9578. Min Act: -0.1700
Data Index: 4434336 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19