Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3815 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.8480. Min Act: -0.1700
Data Index: 580961 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.5980. Min Act: -0.1700
Data Index: 1053340 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.5042. Min Act: -0.1700
Data Index: 4989618 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.5042. Min Act: -0.1700
Data Index: 6326631 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.4417. Min Act: -0.1700
Data Index: 7998992 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.4105. Min Act: -0.1700
Data Index: 4355969 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.3792. Min Act: -0.1700
Data Index: 1346145 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.3792. Min Act: -0.1700
Data Index: 8293382 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.3792. Min Act: -0.1700
Data Index: 7452782 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.3167. Min Act: -0.1700
Data Index: 6618200 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.2855. Min Act: -0.1700
Data Index: 345360 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.2542. Min Act: -0.1700
Data Index: 1876412 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.2230. Min Act: -0.1700
Data Index: 4829856 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.2230. Min Act: -0.1700
Data Index: 4530035 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.1917. Min Act: -0.1700
Data Index: 5232716 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.2542. Min Act: -0.1700
Data Index: 1533786 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.2230. Min Act: -0.1700
Data Index: 7818900 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.1917. Min Act: -0.1700
Data Index: 7346868 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.1605. Min Act: -0.1700
Data Index: 6883448 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8480. Min Range: -6.8480
Max Act: 6.1605. Min Act: -0.1700
Data Index: 1220677 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19