Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2792 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.4826. Min Act: -0.1700
Data Index: 7949350 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.0763. Min Act: -0.1700
Data Index: 4494776 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.0451. Min Act: -0.1700
Data Index: 227708 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.0138. Min Act: -0.1700
Data Index: 8463757 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4826. Min Range: -6.4826
Max Act: 6.0138. Min Act: -0.1700
Data Index: 258725 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4826. Min Range: -6.4826
Max Act: 5.9826. Min Act: -0.1700
Data Index: 5091663 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4826. Min Range: -6.4826
Max Act: 5.9201. Min Act: -0.1700
Data Index: 342054 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4826. Min Range: -6.4826
Max Act: 5.9201. Min Act: -0.1700
Data Index: 6303364 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4826. Min Range: -6.4826
Max Act: 5.8888. Min Act: -0.1700
Data Index: 3220834 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4826. Min Range: -6.4826
Max Act: 5.8888. Min Act: -0.1700
Data Index: 3570882 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4826. Min Range: -6.4826
Max Act: 5.8576. Min Act: -0.1700
Data Index: 2879554 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4826. Min Range: -6.4826
Max Act: 5.8576. Min Act: -0.1700
Data Index: 4080061 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4826. Min Range: -6.4826
Max Act: 5.8263. Min Act: -0.1700
Data Index: 6888943 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4826. Min Range: -6.4826
Max Act: 5.8263. Min Act: -0.1700
Data Index: 1879619 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4826. Min Range: -6.4826
Max Act: 5.8263. Min Act: -0.1700
Data Index: 1865682 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4826. Min Range: -6.4826
Max Act: 5.7951. Min Act: -0.1700
Data Index: 2857375 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4826. Min Range: -6.4826
Max Act: 5.7951. Min Act: -0.1700
Data Index: 6806913 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4826. Min Range: -6.4826
Max Act: 5.7638. Min Act: -0.1700
Data Index: 8147541 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4826. Min Range: -6.4826
Max Act: 5.7951. Min Act: -0.1700
Data Index: 2639725 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4826. Min Range: -6.4826
Max Act: 5.7951. Min Act: -0.1700
Data Index: 4593627 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19