Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 213 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3755. Min Range: -6.3755
Max Act: 6.3755. Min Act: -0.1700
Data Index: 8412481 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3755. Min Range: -6.3755
Max Act: 6.2505. Min Act: -0.1700
Data Index: 5145777 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3755. Min Range: -6.3755
Max Act: 6.2192. Min Act: -0.1700
Data Index: 5650751 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3755. Min Range: -6.3755
Max Act: 6.1567. Min Act: -0.1700
Data Index: 110303 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3755. Min Range: -6.3755
Max Act: 6.0942. Min Act: -0.1700
Data Index: 3364238 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3755. Min Range: -6.3755
Max Act: 6.0317. Min Act: -0.1700
Data Index: 4079501 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3755. Min Range: -6.3755
Max Act: 6.0317. Min Act: -0.1700
Data Index: 7428278 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3755. Min Range: -6.3755
Max Act: 6.0317. Min Act: -0.1700
Data Index: 1832192 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3755. Min Range: -6.3755
Max Act: 5.9692. Min Act: -0.1700
Data Index: 1538752 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3755. Min Range: -6.3755
Max Act: 5.9692. Min Act: -0.1700
Data Index: 1270132 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3755. Min Range: -6.3755
Max Act: 5.9380. Min Act: -0.1700
Data Index: 4646476 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3755. Min Range: -6.3755
Max Act: 5.9067. Min Act: -0.1700
Data Index: 5404402 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3755. Min Range: -6.3755
Max Act: 5.8755. Min Act: -0.1700
Data Index: 6335277 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3755. Min Range: -6.3755
Max Act: 5.8755. Min Act: -0.1700
Data Index: 7988915 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3755. Min Range: -6.3755
Max Act: 5.8755. Min Act: -0.1700
Data Index: 6030894 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3755. Min Range: -6.3755
Max Act: 5.8755. Min Act: -0.1700
Data Index: 5033971 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3755. Min Range: -6.3755
Max Act: 5.8755. Min Act: -0.1700
Data Index: 4242326 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3755. Min Range: -6.3755
Max Act: 5.8442. Min Act: -0.1700
Data Index: 4053235 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3755. Min Range: -6.3755
Max Act: 5.8442. Min Act: -0.1700
Data Index: 284005 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3755. Min Range: -6.3755
Max Act: 5.8442. Min Act: -0.1700
Data Index: 1220401 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19