Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3761 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.3985. Min Act: -0.1700
Data Index: 688081 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.3047. Min Act: -0.1700
Data Index: 6361459 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.3672. Min Act: -0.1700
Data Index: 3252864 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.3672. Min Act: -0.1700
Data Index: 3526997 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.3047. Min Act: -0.1700
Data Index: 80591 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.3047. Min Act: -0.1700
Data Index: 3252865 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.3047. Min Act: -0.1700
Data Index: 5281869 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.3047. Min Act: -0.1700
Data Index: 4259514 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.2422. Min Act: -0.1700
Data Index: 3249168 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.1797. Min Act: -0.1700
Data Index: 3588939 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.1797. Min Act: -0.1700
Data Index: 3541044 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.1485. Min Act: -0.1700
Data Index: 2582783 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.0860. Min Act: -0.1700
Data Index: 6598694 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.0860. Min Act: -0.1700
Data Index: 2467293 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.0547. Min Act: -0.1700
Data Index: 1712572 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.0547. Min Act: -0.1700
Data Index: 1477937 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.0235. Min Act: -0.1700
Data Index: 4967533 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3985. Min Range: -7.3985
Max Act: 7.0547. Min Act: -0.1700
Data Index: 4839921 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3985. Min Range: -7.3985
Max Act: 6.9922. Min Act: -0.1700
Data Index: 2771332 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3985. Min Range: -7.3985
Max Act: 6.9922. Min Act: -0.1700
Data Index: 460626 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19