Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3093 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1169. Min Range: -8.1169
Max Act: 8.1169. Min Act: -0.1700
Data Index: 8585495 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1169. Min Range: -8.1169
Max Act: 8.1169. Min Act: -0.1700
Data Index: 2490810 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.9919. Min Act: -0.1700
Data Index: 3320176 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.8669. Min Act: -0.1700
Data Index: 120283 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.9919. Min Act: -0.1700
Data Index: 4547406 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.8669. Min Act: -0.1700
Data Index: 2142241 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.8669. Min Act: -0.1700
Data Index: 6528160 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.8669. Min Act: -0.1700
Data Index: 1554229 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.8669. Min Act: -0.1700
Data Index: 117881 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.8044. Min Act: -0.1700
Data Index: 6934182 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.8044. Min Act: -0.1700
Data Index: 2219147 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.7419. Min Act: -0.1700
Data Index: 2942301 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.7419. Min Act: -0.1700
Data Index: 3734801 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.7419. Min Act: -0.1700
Data Index: 1234765 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.7419. Min Act: -0.1700
Data Index: 6952101 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.6794. Min Act: -0.1700
Data Index: 6466288 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.6482. Min Act: -0.1700
Data Index: 8275933 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.6169. Min Act: -0.1700
Data Index: 1843356 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.6169. Min Act: -0.1700
Data Index: 7849217 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1169. Min Range: -8.1169
Max Act: 7.5857. Min Act: -0.1700
Data Index: 8447291 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19