Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2806 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.5201. Min Act: -0.1700
Data Index: 198659 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.4263. Min Act: -0.1700
Data Index: 7580610 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3951. Min Act: -0.1700
Data Index: 2942763 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3638. Min Act: -0.1700
Data Index: 263117 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3638. Min Act: -0.1700
Data Index: 8641430 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3638. Min Act: -0.1700
Data Index: 2878269 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3638. Min Act: -0.1700
Data Index: 414484 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3013. Min Act: -0.1700
Data Index: 771433 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3013. Min Act: -0.1700
Data Index: 5734686 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.2388. Min Act: -0.1700
Data Index: 3785372 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.2388. Min Act: -0.1700
Data Index: 7473963 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.2076. Min Act: -0.1700
Data Index: 7300778 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.2076. Min Act: -0.1700
Data Index: 7504601 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.2076. Min Act: -0.1700
Data Index: 6069049 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.1763. Min Act: -0.1700
Data Index: 2293946 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.1763. Min Act: -0.1700
Data Index: 4192187 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.1763. Min Act: -0.1700
Data Index: 7386754 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.1451. Min Act: -0.1700
Data Index: 7002235 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.1451. Min Act: -0.1700
Data Index: 6476038 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.1451. Min Act: -0.1700
Data Index: 2625661 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19