Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 249 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4363. Min Range: -9.4363
Max Act: 9.4363. Min Act: -0.1700
Data Index: 6023121 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4363. Min Range: -9.4363
Max Act: 9.1863. Min Act: -0.1700
Data Index: 7953412 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4363. Min Range: -9.4363
Max Act: 9.1863. Min Act: -0.1700
Data Index: 650975 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4363. Min Range: -9.4363
Max Act: 9.1238. Min Act: -0.1700
Data Index: 8511739 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4363. Min Range: -9.4363
Max Act: 8.9988. Min Act: -0.1700
Data Index: 7511766 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4363. Min Range: -9.4363
Max Act: 8.9363. Min Act: -0.1700
Data Index: 1853966 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4363. Min Range: -9.4363
Max Act: 8.8113. Min Act: -0.1700
Data Index: 8206175 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4363. Min Range: -9.4363
Max Act: 8.6863. Min Act: -0.1700
Data Index: 8206174 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4363. Min Range: -9.4363
Max Act: 8.6863. Min Act: -0.1700
Data Index: 6208019 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4363. Min Range: -9.4363
Max Act: 8.6238. Min Act: -0.1700
Data Index: 3636569 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4363. Min Range: -9.4363
Max Act: 8.6238. Min Act: -0.1700
Data Index: 2677206 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4363. Min Range: -9.4363
Max Act: 8.6238. Min Act: -0.1700
Data Index: 347295 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4363. Min Range: -9.4363
Max Act: 8.5613. Min Act: -0.1700
Data Index: 2247513 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4363. Min Range: -9.4363
Max Act: 8.5613. Min Act: -0.1700
Data Index: 593563 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4363. Min Range: -9.4363
Max Act: 8.5613. Min Act: -0.1700
Data Index: 97486 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4363. Min Range: -9.4363
Max Act: 8.5613. Min Act: -0.1700
Data Index: 7649708 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4363. Min Range: -9.4363
Max Act: 8.4988. Min Act: -0.1700
Data Index: 752143 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4363. Min Range: -9.4363
Max Act: 8.4988. Min Act: -0.1700
Data Index: 1326462 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4363. Min Range: -9.4363
Max Act: 8.4988. Min Act: -0.1700
Data Index: 420012 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4363. Min Range: -9.4363
Max Act: 8.4988. Min Act: -0.1700
Data Index: 4471934 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19