Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2218 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.2291. Min Act: -0.1700
Data Index: 7247894 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.2291. Min Act: -0.1700
Data Index: 4660018 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.1978. Min Act: -0.1700
Data Index: 7247895 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.1353. Min Act: -0.1700
Data Index: 8272351 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.1353. Min Act: -0.1700
Data Index: 3200461 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.0416. Min Act: -0.1700
Data Index: 7675227 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.9478. Min Act: -0.1700
Data Index: 2308745 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.9478. Min Act: -0.1700
Data Index: 3365966 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.9478. Min Act: -0.1700
Data Index: 446073 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.9478. Min Act: -0.1700
Data Index: 8565040 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.8853. Min Act: -0.1700
Data Index: 5768934 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.9166. Min Act: -0.1700
Data Index: 6870067 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.8853. Min Act: -0.1700
Data Index: 5102551 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.8853. Min Act: -0.1700
Data Index: 7178718 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.8853. Min Act: -0.1700
Data Index: 685268 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.8541. Min Act: -0.1700
Data Index: 2032178 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.8541. Min Act: -0.1700
Data Index: 4292666 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.8541. Min Act: -0.1700
Data Index: 4778404 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.8541. Min Act: -0.1700
Data Index: 5070076 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.8228. Min Act: -0.1700
Data Index: 3136074 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19