Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4482 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2795. Min Range: -11.2795
Max Act: 11.2795. Min Act: -0.1700
Data Index: 556711 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2795. Min Range: -11.2795
Max Act: 11.2170. Min Act: -0.1700
Data Index: 2273467 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2795. Min Range: -11.2795
Max Act: 11.1545. Min Act: -0.1700
Data Index: 2799456 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2795. Min Range: -11.2795
Max Act: 11.0920. Min Act: -0.1700
Data Index: 994618 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2795. Min Range: -11.2795
Max Act: 11.0295. Min Act: -0.1700
Data Index: 2957091 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2795. Min Range: -11.2795
Max Act: 10.9670. Min Act: -0.1700
Data Index: 6716304 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2795. Min Range: -11.2795
Max Act: 10.8420. Min Act: -0.1700
Data Index: 8422623 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2795. Min Range: -11.2795
Max Act: 10.9045. Min Act: -0.1700
Data Index: 7730760 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2795. Min Range: -11.2795
Max Act: 10.8420. Min Act: -0.1700
Data Index: 6254641 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2795. Min Range: -11.2795
Max Act: 10.8420. Min Act: -0.1700
Data Index: 5831325 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2795. Min Range: -11.2795
Max Act: 10.7795. Min Act: -0.1700
Data Index: 1506001 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2795. Min Range: -11.2795
Max Act: 10.7795. Min Act: -0.1700
Data Index: 8749888 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2795. Min Range: -11.2795
Max Act: 10.8420. Min Act: -0.1700
Data Index: 4071918 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2795. Min Range: -11.2795
Max Act: 10.7170. Min Act: -0.1700
Data Index: 4416688 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2795. Min Range: -11.2795
Max Act: 10.7170. Min Act: -0.1700
Data Index: 4396557 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2795. Min Range: -11.2795
Max Act: 10.5920. Min Act: -0.1700
Data Index: 8331813 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2795. Min Range: -11.2795
Max Act: 10.5920. Min Act: -0.1700
Data Index: 8133114 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2795. Min Range: -11.2795
Max Act: 10.5920. Min Act: -0.1700
Data Index: 7580202 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2795. Min Range: -11.2795
Max Act: 10.4670. Min Act: -0.1700
Data Index: 2736691 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2795. Min Range: -11.2795
Max Act: 10.5295. Min Act: -0.1700
Data Index: 485732 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19