Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4784 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.8294. Min Act: -0.1700
Data Index: 6691074 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.4856. Min Act: -0.1700
Data Index: 7897766 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.5169. Min Act: -0.1700
Data Index: 8598291 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.4856. Min Act: -0.1700
Data Index: 7855574 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.4856. Min Act: -0.1700
Data Index: 2245847 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.3919. Min Act: -0.1700
Data Index: 2006075 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.3606. Min Act: -0.1700
Data Index: 8136757 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.3294. Min Act: -0.1700
Data Index: 3299518 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.2981. Min Act: -0.1700
Data Index: 2479850 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.2981. Min Act: -0.1700
Data Index: 6874152 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.2669. Min Act: -0.1700
Data Index: 6512397 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.2356. Min Act: -0.1700
Data Index: 3229644 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.2356. Min Act: -0.1700
Data Index: 6197640 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.2356. Min Act: -0.1700
Data Index: 6350864 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.2356. Min Act: -0.1700
Data Index: 5792850 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.1731. Min Act: -0.1700
Data Index: 3455060 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.1731. Min Act: -0.1700
Data Index: 723942 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.1731. Min Act: -0.1700
Data Index: 5772898 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.1419. Min Act: -0.1700
Data Index: 8000877 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.1731. Min Act: -0.1700
Data Index: 8045487 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19