Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4616 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5942. Min Range: -9.5942
Max Act: 9.5942. Min Act: -0.1700
Data Index: 6709984 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5942. Min Range: -9.5942
Max Act: 8.5942. Min Act: -0.1700
Data Index: 2973288 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5942. Min Range: -9.5942
Max Act: 8.5942. Min Act: -0.1700
Data Index: 755519 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5942. Min Range: -9.5942
Max Act: 8.5317. Min Act: -0.1699
Data Index: 3465575 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5942. Min Range: -9.5942
Max Act: 8.4067. Min Act: -0.1700
Data Index: 519733 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5942. Min Range: -9.5942
Max Act: 8.2817. Min Act: -0.1700
Data Index: 2360133 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5942. Min Range: -9.5942
Max Act: 8.2817. Min Act: -0.1700
Data Index: 8538064 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5942. Min Range: -9.5942
Max Act: 8.2817. Min Act: -0.1700
Data Index: 163979 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5942. Min Range: -9.5942
Max Act: 8.2192. Min Act: -0.1700
Data Index: 6274462 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5942. Min Range: -9.5942
Max Act: 8.1567. Min Act: -0.1700
Data Index: 2463283 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5942. Min Range: -9.5942
Max Act: 8.0942. Min Act: -0.1700
Data Index: 1970763 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5942. Min Range: -9.5942
Max Act: 8.0942. Min Act: -0.1700
Data Index: 3813610 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5942. Min Range: -9.5942
Max Act: 8.1567. Min Act: -0.1700
Data Index: 895225 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5942. Min Range: -9.5942
Max Act: 8.1567. Min Act: -0.1699
Data Index: 2721858 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5942. Min Range: -9.5942
Max Act: 8.0317. Min Act: -0.1700
Data Index: 1861872 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5942. Min Range: -9.5942
Max Act: 8.0317. Min Act: -0.1700
Data Index: 4306344 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5942. Min Range: -9.5942
Max Act: 7.9692. Min Act: -0.1700
Data Index: 6303120 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5942. Min Range: -9.5942
Max Act: 7.9692. Min Act: -0.1700
Data Index: 5367188 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5942. Min Range: -9.5942
Max Act: 7.9692. Min Act: -0.1700
Data Index: 6244983 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5942. Min Range: -9.5942
Max Act: 7.9692. Min Act: -0.1700
Data Index: 4000808 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19