Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1432. Min Range: -4.1432
Max Act: 4.1432. Min Act: -0.1700
Data Index: 187895 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1432. Min Range: -4.1432
Max Act: 4.1432. Min Act: -0.1700
Data Index: 6472978 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1432. Min Range: -4.1432
Max Act: 4.1119. Min Act: -0.1700
Data Index: 5326211 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1432. Min Range: -4.1432
Max Act: 4.0181. Min Act: -0.1700
Data Index: 7417705 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1432. Min Range: -4.1432
Max Act: 4.0494. Min Act: -0.1700
Data Index: 541088 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1432. Min Range: -4.1432
Max Act: 4.0181. Min Act: -0.1700
Data Index: 4566473 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1432. Min Range: -4.1432
Max Act: 4.0181. Min Act: -0.1700
Data Index: 2473834 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1432. Min Range: -4.1432
Max Act: 3.9556. Min Act: -0.1700
Data Index: 7357198 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1432. Min Range: -4.1432
Max Act: 3.9556. Min Act: -0.1700
Data Index: 4485900 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1432. Min Range: -4.1432
Max Act: 3.9244. Min Act: -0.1700
Data Index: 5476503 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1432. Min Range: -4.1432
Max Act: 3.9244. Min Act: -0.1700
Data Index: 3884385 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1432. Min Range: -4.1432
Max Act: 3.9244. Min Act: -0.1700
Data Index: 5943800 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1432. Min Range: -4.1432
Max Act: 3.8931. Min Act: -0.1700
Data Index: 8662545 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1432. Min Range: -4.1432
Max Act: 3.8931. Min Act: -0.1700
Data Index: 1020408 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1432. Min Range: -4.1432
Max Act: 3.8931. Min Act: -0.1700
Data Index: 5977922 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1432. Min Range: -4.1432
Max Act: 3.8618. Min Act: -0.1700
Data Index: 7619147 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1432. Min Range: -4.1432
Max Act: 3.8618. Min Act: -0.1700
Data Index: 7356538 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1432. Min Range: -4.1432
Max Act: 3.8618. Min Act: -0.1700
Data Index: 347688 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1432. Min Range: -4.1432
Max Act: 3.8618. Min Act: -0.1700
Data Index: 5384960 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1432. Min Range: -4.1432
Max Act: 3.8931. Min Act: -0.1700
Data Index: 2431630 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19