Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6190 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.6738. Min Act: -0.1700
Data Index: 7695526 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.6113. Min Act: -0.1700
Data Index: 6360315 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.5801. Min Act: -0.1700
Data Index: 840967 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.5801. Min Act: -0.1700
Data Index: 3592095 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.5488. Min Act: -0.1700
Data Index: 6743619 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.5488. Min Act: -0.1700
Data Index: 3979523 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.5176. Min Act: -0.1700
Data Index: 6037659 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.4238. Min Act: -0.1700
Data Index: 2545945 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.3926. Min Act: -0.1700
Data Index: 664762 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.4238. Min Act: -0.1700
Data Index: 8402349 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.3926. Min Act: -0.1700
Data Index: 6743618 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.3926. Min Act: -0.1700
Data Index: 4685438 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.3613. Min Act: -0.1700
Data Index: 6037660 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.3301. Min Act: -0.1700
Data Index: 4242139 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.3613. Min Act: -0.1700
Data Index: 6204644 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.3613. Min Act: -0.1700
Data Index: 7737414 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.3613. Min Act: -0.1700
Data Index: 1199307 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.3301. Min Act: -0.1700
Data Index: 7501240 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.3613. Min Act: -0.1700
Data Index: 473616 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6738. Min Range: -4.6738
Max Act: 4.2988. Min Act: -0.1700
Data Index: 2506850 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19