Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4237 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.5201. Min Act: -0.1700
Data Index: 7122327 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3639. Min Act: -0.1700
Data Index: 3190276 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3326. Min Act: -0.1700
Data Index: 6870511 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3326. Min Act: -0.1700
Data Index: 878323 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3326. Min Act: -0.1700
Data Index: 4028712 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3326. Min Act: -0.1700
Data Index: 6160609 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3014. Min Act: -0.1700
Data Index: 1316063 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3014. Min Act: -0.1700
Data Index: 4894586 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3014. Min Act: -0.1700
Data Index: 3654394 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3014. Min Act: -0.1700
Data Index: 3089136 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3014. Min Act: -0.1700
Data Index: 3204356 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.2701. Min Act: -0.1700
Data Index: 1496303 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.2701. Min Act: -0.1700
Data Index: 6784320 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.2701. Min Act: -0.1700
Data Index: 7051456 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.2701. Min Act: -0.1700
Data Index: 3018471 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.2701. Min Act: -0.1700
Data Index: 7180947 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.2701. Min Act: -0.1700
Data Index: 5165994 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.3014. Min Act: -0.1700
Data Index: 2611723 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.2389. Min Act: -0.1700
Data Index: 1096435 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5201. Min Range: -5.5201
Max Act: 5.2389. Min Act: -0.1700
Data Index: 783620 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19