Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3804 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.6626. Min Act: -0.1700
Data Index: 3001833 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.4751. Min Act: -0.1700
Data Index: 6766988 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.4439. Min Act: -0.1700
Data Index: 2531419 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.4439. Min Act: -0.1700
Data Index: 4459890 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.4439. Min Act: -0.1700
Data Index: 8238725 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.4439. Min Act: -0.1700
Data Index: 8744205 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.4126. Min Act: -0.1700
Data Index: 3128367 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.4126. Min Act: -0.1700
Data Index: 1038239 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.3814. Min Act: -0.1700
Data Index: 1599360 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.3814. Min Act: -0.1700
Data Index: 1294363 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.3814. Min Act: -0.1700
Data Index: 8616457 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.3814. Min Act: -0.1700
Data Index: 8194773 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.3189. Min Act: -0.1700
Data Index: 4640009 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.3189. Min Act: -0.1700
Data Index: 1450636 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.2876. Min Act: -0.1700
Data Index: 8217721 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.2564. Min Act: -0.1700
Data Index: 6316160 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.2564. Min Act: -0.1700
Data Index: 5186706 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.2876. Min Act: -0.1700
Data Index: 6597736 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.2876. Min Act: -0.1700
Data Index: 6936865 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6626. Min Range: -5.6626
Max Act: 5.2564. Min Act: -0.1700
Data Index: 5315488 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19