Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4491 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1228. Min Range: -5.1228
Max Act: 5.1228. Min Act: -0.1700
Data Index: 1872367 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1228. Min Range: -5.1228
Max Act: 5.1228. Min Act: -0.1700
Data Index: 4209745 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1228. Min Range: -5.1228
Max Act: 5.0603. Min Act: -0.1700
Data Index: 7642770 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1228. Min Range: -5.1228
Max Act: 4.9978. Min Act: -0.1700
Data Index: 1066458 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1228. Min Range: -5.1228
Max Act: 4.9040. Min Act: -0.1700
Data Index: 7859320 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1228. Min Range: -5.1228
Max Act: 4.8728. Min Act: -0.1700
Data Index: 3331427 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1228. Min Range: -5.1228
Max Act: 4.9040. Min Act: -0.1700
Data Index: 5057158 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1228. Min Range: -5.1228
Max Act: 4.9040. Min Act: -0.1700
Data Index: 1158784 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1228. Min Range: -5.1228
Max Act: 4.9040. Min Act: -0.1700
Data Index: 2544239 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1228. Min Range: -5.1228
Max Act: 4.9040. Min Act: -0.1700
Data Index: 85510 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1228. Min Range: -5.1228
Max Act: 4.8728. Min Act: -0.1700
Data Index: 2730463 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1228. Min Range: -5.1228
Max Act: 4.8415. Min Act: -0.1700
Data Index: 2934191 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1228. Min Range: -5.1228
Max Act: 4.8728. Min Act: -0.1700
Data Index: 7205744 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1228. Min Range: -5.1228
Max Act: 4.8103. Min Act: -0.1700
Data Index: 2711657 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1228. Min Range: -5.1228
Max Act: 4.8415. Min Act: -0.1700
Data Index: 5502799 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1228. Min Range: -5.1228
Max Act: 4.8103. Min Act: -0.1700
Data Index: 5262441 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1228. Min Range: -5.1228
Max Act: 4.8103. Min Act: -0.1700
Data Index: 6712056 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1228. Min Range: -5.1228
Max Act: 4.8103. Min Act: -0.1700
Data Index: 6688961 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1228. Min Range: -5.1228
Max Act: 4.7790. Min Act: -0.1700
Data Index: 6988249 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1228. Min Range: -5.1228
Max Act: 4.7790. Min Act: -0.1700
Data Index: 934892 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19