Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3963 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.9350. Min Act: -0.1700
Data Index: 7109920 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.7475. Min Act: -0.1700
Data Index: 1471170 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.7475. Min Act: -0.1700
Data Index: 145117 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.6850. Min Act: -0.1700
Data Index: 2056944 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.7162. Min Act: -0.1700
Data Index: 2308619 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.6537. Min Act: -0.1700
Data Index: 4411254 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.6850. Min Act: -0.1700
Data Index: 7823243 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.6225. Min Act: -0.1700
Data Index: 1753323 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.6225. Min Act: -0.1700
Data Index: 6663316 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.5600. Min Act: -0.1700
Data Index: 7918061 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.5600. Min Act: -0.1700
Data Index: 79249 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.5600. Min Act: -0.1700
Data Index: 5137427 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.5287. Min Act: -0.1700
Data Index: 814358 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.5287. Min Act: -0.1700
Data Index: 6111594 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.5287. Min Act: -0.1700
Data Index: 1194801 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.5287. Min Act: -0.1700
Data Index: 1719980 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.5287. Min Act: -0.1700
Data Index: 375879 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.5287. Min Act: -0.1700
Data Index: 4439380 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.4975. Min Act: -0.1700
Data Index: 4220919 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9350. Min Range: -5.9350
Max Act: 5.4975. Min Act: -0.1700
Data Index: 1241605 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19