Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3380 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.5475. Min Act: -0.1700
Data Index: 970509 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.5163. Min Act: -0.1700
Data Index: 8633986 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.4225. Min Act: -0.1700
Data Index: 2525714 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.3913. Min Act: -0.1700
Data Index: 5782034 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.2975. Min Act: -0.1700
Data Index: 1930220 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.2975. Min Act: -0.1700
Data Index: 6288085 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.2663. Min Act: -0.1700
Data Index: 5419593 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.2350. Min Act: -0.1700
Data Index: 5598965 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.2350. Min Act: -0.1700
Data Index: 135208 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.2350. Min Act: -0.1700
Data Index: 8360333 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.2350. Min Act: -0.1700
Data Index: 8605002 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.2038. Min Act: -0.1700
Data Index: 1169220 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.2038. Min Act: -0.1700
Data Index: 1274681 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.1725. Min Act: -0.1700
Data Index: 5301276 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.1725. Min Act: -0.1700
Data Index: 1861622 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.1725. Min Act: -0.1700
Data Index: 73876 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.1413. Min Act: -0.1700
Data Index: 1264712 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.1413. Min Act: -0.1700
Data Index: 4365237 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.1413. Min Act: -0.1700
Data Index: 1028480 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5475. Min Range: -5.5475
Max Act: 5.1100. Min Act: -0.1700
Data Index: 6942970 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19