Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5076 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1097. Min Range: -5.1097
Max Act: 5.1097. Min Act: -0.1700
Data Index: 1909427 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1097. Min Range: -5.1097
Max Act: 5.1097. Min Act: -0.1700
Data Index: 94330 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.8910. Min Act: -0.1700
Data Index: 564121 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.7972. Min Act: -0.1700
Data Index: 3847496 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.7035. Min Act: -0.1700
Data Index: 8284270 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.7035. Min Act: -0.1700
Data Index: 1632370 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.6410. Min Act: -0.1700
Data Index: 6756120 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.6410. Min Act: -0.1700
Data Index: 7440365 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.6097. Min Act: -0.1700
Data Index: 7324621 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.5785. Min Act: -0.1700
Data Index: 3737655 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.5785. Min Act: -0.1700
Data Index: 4919355 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.5785. Min Act: -0.1700
Data Index: 3961276 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.5472. Min Act: -0.1700
Data Index: 5674837 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.5472. Min Act: -0.1700
Data Index: 7979664 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.5472. Min Act: -0.1700
Data Index: 2448177 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.5472. Min Act: -0.1700
Data Index: 765392 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.5160. Min Act: -0.1700
Data Index: 2738261 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.5160. Min Act: -0.1700
Data Index: 5486289 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.5160. Min Act: -0.1700
Data Index: 1084215 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1097. Min Range: -5.1097
Max Act: 4.4222. Min Act: -0.1700
Data Index: 2119211 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19