Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2835 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1660. Min Range: -5.1660
Max Act: 5.1660. Min Act: -0.1700
Data Index: 8265362 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1660. Min Range: -5.1660
Max Act: 5.0722. Min Act: -0.1700
Data Index: 8014203 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1660. Min Range: -5.1660
Max Act: 5.0410. Min Act: -0.1700
Data Index: 802090 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1660. Min Range: -5.1660
Max Act: 4.9785. Min Act: -0.1700
Data Index: 8265351 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1660. Min Range: -5.1660
Max Act: 4.9785. Min Act: -0.1700
Data Index: 8265356 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1660. Min Range: -5.1660
Max Act: 5.0097. Min Act: -0.1700
Data Index: 7095517 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1660. Min Range: -5.1660
Max Act: 4.9785. Min Act: -0.1700
Data Index: 357181 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1660. Min Range: -5.1660
Max Act: 4.9160. Min Act: -0.1700
Data Index: 5506573 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1660. Min Range: -5.1660
Max Act: 4.9160. Min Act: -0.1700
Data Index: 8265353 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1660. Min Range: -5.1660
Max Act: 4.9160. Min Act: -0.1700
Data Index: 4277047 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1660. Min Range: -5.1660
Max Act: 4.9160. Min Act: -0.1700
Data Index: 8265358 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1660. Min Range: -5.1660
Max Act: 4.9160. Min Act: -0.1700
Data Index: 6211142 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1660. Min Range: -5.1660
Max Act: 4.8847. Min Act: -0.1700
Data Index: 8265348 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1660. Min Range: -5.1660
Max Act: 4.8847. Min Act: -0.1700
Data Index: 1553254 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1660. Min Range: -5.1660
Max Act: 4.8847. Min Act: -0.1700
Data Index: 3279081 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1660. Min Range: -5.1660
Max Act: 4.8222. Min Act: -0.1700
Data Index: 357177 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1660. Min Range: -5.1660
Max Act: 4.8222. Min Act: -0.1700
Data Index: 4119335 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1660. Min Range: -5.1660
Max Act: 4.8535. Min Act: -0.1700
Data Index: 4888589 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1660. Min Range: -5.1660
Max Act: 4.8535. Min Act: -0.1700
Data Index: 8265359 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1660. Min Range: -5.1660
Max Act: 4.7597. Min Act: -0.1700
Data Index: 2051219 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19