Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5291 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3194. Min Range: -8.3194
Max Act: 8.3194. Min Act: -0.1700
Data Index: 3835598 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.9444. Min Act: -0.1700
Data Index: 4206138 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.9444. Min Act: -0.1700
Data Index: 5102639 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.8819. Min Act: -0.1700
Data Index: 6002903 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.9131. Min Act: -0.1700
Data Index: 1996900 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.8506. Min Act: -0.1700
Data Index: 8552922 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.8506. Min Act: -0.1700
Data Index: 3496570 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.8506. Min Act: -0.1700
Data Index: 8135962 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.8194. Min Act: -0.1700
Data Index: 7715753 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.7881. Min Act: -0.1700
Data Index: 3692382 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.8194. Min Act: -0.1700
Data Index: 4362890 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.7881. Min Act: -0.1700
Data Index: 4956034 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.7569. Min Act: -0.1700
Data Index: 558105 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.7256. Min Act: -0.1700
Data Index: 443534 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.6631. Min Act: -0.1700
Data Index: 1791086 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.6319. Min Act: -0.1700
Data Index: 7214253 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.6006. Min Act: -0.1700
Data Index: 3404649 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.5381. Min Act: -0.1700
Data Index: 1135326 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.5381. Min Act: -0.1700
Data Index: 5600249 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3194. Min Range: -8.3194
Max Act: 7.5381. Min Act: -0.1700
Data Index: 8686065 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19