Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1071 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.7854. Min Act: -0.1700
Data Index: 4844505 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.6604. Min Act: -0.1700
Data Index: 4967638 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.6292. Min Act: -0.1700
Data Index: 7846782 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.5667. Min Act: -0.1700
Data Index: 7184341 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.5042. Min Act: -0.1700
Data Index: 5589115 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.5042. Min Act: -0.1700
Data Index: 1810044 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.4729. Min Act: -0.1700
Data Index: 7660627 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.4417. Min Act: -0.1700
Data Index: 7781552 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.4104. Min Act: -0.1700
Data Index: 8414897 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.4417. Min Act: -0.1700
Data Index: 2265557 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.4104. Min Act: -0.1700
Data Index: 7832734 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.3792. Min Act: -0.1700
Data Index: 3707998 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.3792. Min Act: -0.1700
Data Index: 5527924 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.3792. Min Act: -0.1700
Data Index: 8498249 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.3792. Min Act: -0.1700
Data Index: 8629679 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.3479. Min Act: -0.1700
Data Index: 904257 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.3479. Min Act: -0.1700
Data Index: 3124067 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.3479. Min Act: -0.1700
Data Index: 1566669 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.3479. Min Act: -0.1700
Data Index: 757782 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7854. Min Range: -5.7854
Max Act: 5.3479. Min Act: -0.1700
Data Index: 3437477 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19