Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4225 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.3597. Min Act: -0.1700
Data Index: 6730071 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.3244. Min Act: -0.1700
Data Index: 1437968 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.3421. Min Act: -0.1700
Data Index: 1437963 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.2891. Min Act: -0.1700
Data Index: 7845348 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.2715. Min Act: -0.1695
Data Index: 1198350 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.2891. Min Act: -0.1699
Data Index: 5909461 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.2715. Min Act: -0.1700
Data Index: 6771881 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.2362. Min Act: -0.1700
Data Index: 1437950 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.2186. Min Act: -0.1698
Data Index: 7502848 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.2186. Min Act: -0.1700
Data Index: 5221356 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.2186. Min Act: -0.1700
Data Index: 3427651 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.2010. Min Act: -0.1700
Data Index: 4550889 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.1834. Min Act: -0.1691
Data Index: 5865084 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.1658. Min Act: -0.1700
Data Index: 434792 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.1834. Min Act: -0.1700
Data Index: 2033700 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.1834. Min Act: -0.1700
Data Index: 4799130 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.1658. Min Act: -0.1700
Data Index: 3259402 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.1834. Min Act: -0.1698
Data Index: 1852484 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.1834. Min Act: -0.1700
Data Index: 4765527 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3597. Min Range: -1.3597
Max Act: 1.1834. Min Act: -0.1700
Data Index: 501983 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19