Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.6573. Min Act: -0.1700
Data Index: 7254777 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.6260. Min Act: -0.1700
Data Index: 6232528 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.6260. Min Act: -0.1700
Data Index: 8100114 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.6260. Min Act: -0.1700
Data Index: 1231651 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.5948. Min Act: -0.1700
Data Index: 2068227 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.5948. Min Act: -0.1700
Data Index: 5278626 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.5948. Min Act: -0.1699
Data Index: 7773269 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.5635. Min Act: -0.1700
Data Index: 1956069 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.5635. Min Act: -0.1700
Data Index: 1612350 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.5635. Min Act: -0.1700
Data Index: 3589291 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.5948. Min Act: -0.1700
Data Index: 4200920 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.5323. Min Act: -0.1700
Data Index: 4962575 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.5323. Min Act: -0.1700
Data Index: 8698717 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.5635. Min Act: -0.1700
Data Index: 8188759 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.5323. Min Act: -0.1700
Data Index: 4951632 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.5323. Min Act: -0.1700
Data Index: 2657543 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.5323. Min Act: -0.1700
Data Index: 5867136 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.5010. Min Act: -0.1700
Data Index: 2421439 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.5323. Min Act: -0.1700
Data Index: 5087075 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6573. Min Range: -5.6573
Max Act: 5.5635. Min Act: -0.1700
Data Index: 4172705 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19