Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2549 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2317. Min Range: -9.2317
Max Act: 9.2317. Min Act: -0.1700
Data Index: 7502161 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.9817. Min Act: -0.1700
Data Index: 7847074 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.8567. Min Act: -0.1700
Data Index: 2228277 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.9192. Min Act: -0.1700
Data Index: 6739006 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.7942. Min Act: -0.1700
Data Index: 6518019 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.7942. Min Act: -0.1700
Data Index: 4752902 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.7942. Min Act: -0.1700
Data Index: 3848394 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.7317. Min Act: -0.1700
Data Index: 2228282 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.7317. Min Act: -0.1700
Data Index: 5797074 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.7317. Min Act: -0.1700
Data Index: 7237936 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.6692. Min Act: -0.1700
Data Index: 4642323 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.6692. Min Act: -0.1700
Data Index: 2228278 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.6692. Min Act: -0.1700
Data Index: 3423488 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.6692. Min Act: -0.1700
Data Index: 2228279 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.6692. Min Act: -0.1700
Data Index: 6395837 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.6692. Min Act: -0.1700
Data Index: 6255296 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.6692. Min Act: -0.1700
Data Index: 235170 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.6067. Min Act: -0.1700
Data Index: 1847158 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.5442. Min Act: -0.1700
Data Index: 1382684 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2317. Min Range: -9.2317
Max Act: 8.5442. Min Act: -0.1700
Data Index: 2228288 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19