Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0005. Min Range: -6.0005
Max Act: 6.0005. Min Act: -0.1700
Data Index: 1401647 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.9380. Min Act: -0.1700
Data Index: 8714484 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.8755. Min Act: -0.1700
Data Index: 3714670 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.8443. Min Act: -0.1700
Data Index: 8614462 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.7818. Min Act: -0.1700
Data Index: 458246 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.7818. Min Act: -0.1700
Data Index: 6494791 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.7818. Min Act: -0.1700
Data Index: 4151317 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.7505. Min Act: -0.1700
Data Index: 8175995 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.7505. Min Act: -0.1700
Data Index: 5215976 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.7505. Min Act: -0.1700
Data Index: 4411695 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.7505. Min Act: -0.1700
Data Index: 8685273 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.7505. Min Act: -0.1700
Data Index: 5054505 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.7193. Min Act: -0.1700
Data Index: 2674634 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.7818. Min Act: -0.1700
Data Index: 2516429 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.7505. Min Act: -0.1700
Data Index: 7534381 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.6880. Min Act: -0.1700
Data Index: 7456141 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.6880. Min Act: -0.1700
Data Index: 7279311 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.6880. Min Act: -0.1700
Data Index: 6476750 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.6880. Min Act: -0.1700
Data Index: 8375202 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0005. Min Range: -6.0005
Max Act: 5.7193. Min Act: -0.1700
Data Index: 6873481 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19