Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2910 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6969. Min Range: -5.6969
Max Act: 5.6969. Min Act: -0.1700
Data Index: 331654 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6969. Min Range: -5.6969
Max Act: 5.3219. Min Act: -0.1700
Data Index: 1271387 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6969. Min Range: -5.6969
Max Act: 5.2594. Min Act: -0.1700
Data Index: 733429 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6969. Min Range: -5.6969
Max Act: 5.1344. Min Act: -0.1700
Data Index: 1153940 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6969. Min Range: -5.6969
Max Act: 5.1032. Min Act: -0.1700
Data Index: 533611 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6969. Min Range: -5.6969
Max Act: 5.1032. Min Act: -0.1700
Data Index: 7628251 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6969. Min Range: -5.6969
Max Act: 5.0407. Min Act: -0.1700
Data Index: 8434522 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6969. Min Range: -5.6969
Max Act: 5.0719. Min Act: -0.1700
Data Index: 64993 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6969. Min Range: -5.6969
Max Act: 5.0094. Min Act: -0.1700
Data Index: 1044850 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6969. Min Range: -5.6969
Max Act: 5.0094. Min Act: -0.1700
Data Index: 6713693 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6969. Min Range: -5.6969
Max Act: 5.0094. Min Act: -0.1700
Data Index: 7130165 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6969. Min Range: -5.6969
Max Act: 5.0094. Min Act: -0.1700
Data Index: 6798444 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6969. Min Range: -5.6969
Max Act: 4.9782. Min Act: -0.1700
Data Index: 8601197 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6969. Min Range: -5.6969
Max Act: 4.9469. Min Act: -0.1700
Data Index: 1346143 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6969. Min Range: -5.6969
Max Act: 4.9469. Min Act: -0.1700
Data Index: 6671742 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6969. Min Range: -5.6969
Max Act: 4.9157. Min Act: -0.1700
Data Index: 1517659 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6969. Min Range: -5.6969
Max Act: 4.9157. Min Act: -0.1700
Data Index: 2159398 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6969. Min Range: -5.6969
Max Act: 4.9157. Min Act: -0.1700
Data Index: 6939229 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6969. Min Range: -5.6969
Max Act: 4.9157. Min Act: -0.1700
Data Index: 5496447 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6969. Min Range: -5.6969
Max Act: 4.8844. Min Act: -0.1700
Data Index: 6318839 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19