Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2448 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2530. Min Range: -2.2530
Max Act: 2.2530. Min Act: -0.1688
Data Index: 1060698 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2530. Min Range: -2.2530
Max Act: 2.2365. Min Act: -0.1700
Data Index: 4136050 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2530. Min Range: -2.2530
Max Act: 2.1868. Min Act: -0.1700
Data Index: 2294989 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2530. Min Range: -2.2530
Max Act: 2.1702. Min Act: -0.1697
Data Index: 4815303 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2530. Min Range: -2.2530
Max Act: 2.1368. Min Act: -0.1700
Data Index: 6341618 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2530. Min Range: -2.2530
Max Act: 2.1368. Min Act: -0.1700
Data Index: 4324024 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2530. Min Range: -2.2530
Max Act: 2.1201. Min Act: -0.1595
Data Index: 7516613 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2530. Min Range: -2.2530
Max Act: 2.1201. Min Act: -0.1700
Data Index: 8720608 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2530. Min Range: -2.2530
Max Act: 2.1034. Min Act: -0.1696
Data Index: 8697685 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2530. Min Range: -2.2530
Max Act: 2.1034. Min Act: -0.1700
Data Index: 5285410 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2530. Min Range: -2.2530
Max Act: 2.0362. Min Act: -0.1698
Data Index: 7563520 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2530. Min Range: -2.2530
Max Act: 2.0531. Min Act: -0.1700
Data Index: 779511 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2530. Min Range: -2.2530
Max Act: 2.0531. Min Act: -0.1697
Data Index: 1287469 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2530. Min Range: -2.2530
Max Act: 2.0362. Min Act: -0.1698
Data Index: 779509 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2530. Min Range: -2.2530
Max Act: 2.0194. Min Act: -0.1700
Data Index: 6420464 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2530. Min Range: -2.2530
Max Act: 2.0025. Min Act: -0.1687
Data Index: 8393939 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2530. Min Range: -2.2530
Max Act: 1.9856. Min Act: -0.1691
Data Index: 4775663 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2530. Min Range: -2.2530
Max Act: 1.9856. Min Act: -0.1692
Data Index: 8393943 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2530. Min Range: -2.2530
Max Act: 1.9856. Min Act: -0.1700
Data Index: 555144 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2530. Min Range: -2.2530
Max Act: 1.9856. Min Act: -0.1673
Data Index: 7238340 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19