Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3656 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1462. Min Range: -6.1462
Max Act: 6.1462. Min Act: -0.1700
Data Index: 7395801 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.8025. Min Act: -0.1700
Data Index: 81818 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.7400. Min Act: -0.1700
Data Index: 1826691 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.7712. Min Act: -0.1700
Data Index: 5988366 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.7400. Min Act: -0.1700
Data Index: 5989470 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.7087. Min Act: -0.1700
Data Index: 123790 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.6775. Min Act: -0.1700
Data Index: 1232130 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.6462. Min Act: -0.1700
Data Index: 3281265 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.6462. Min Act: -0.1700
Data Index: 5087238 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.5837. Min Act: -0.1700
Data Index: 4902364 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.5525. Min Act: -0.1700
Data Index: 1204842 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.5525. Min Act: -0.1700
Data Index: 8066473 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.5525. Min Act: -0.1700
Data Index: 3306618 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.5212. Min Act: -0.1700
Data Index: 444236 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.4587. Min Act: -0.1700
Data Index: 5713657 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.4900. Min Act: -0.1700
Data Index: 3773135 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.4587. Min Act: -0.1700
Data Index: 1916040 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.4275. Min Act: -0.1700
Data Index: 7515277 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.4275. Min Act: -0.1700
Data Index: 4715778 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.4275. Min Act: -0.1700
Data Index: 2987064 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19