Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1640 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.7542. Min Act: -0.1700
Data Index: 6474107 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.7542. Min Act: -0.1700
Data Index: 142424 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.6917. Min Act: -0.1700
Data Index: 6585349 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.7229. Min Act: -0.1700
Data Index: 5800724 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.6917. Min Act: -0.1700
Data Index: 1635166 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.7229. Min Act: -0.1700
Data Index: 6182340 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.6604. Min Act: -0.1700
Data Index: 3907989 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.6604. Min Act: -0.1700
Data Index: 4630074 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.6604. Min Act: -0.1700
Data Index: 1403447 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.6292. Min Act: -0.1700
Data Index: 3398361 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.5979. Min Act: -0.1700
Data Index: 6508097 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.5979. Min Act: -0.1700
Data Index: 2502624 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.5979. Min Act: -0.1700
Data Index: 351564 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.5667. Min Act: -0.1700
Data Index: 1888620 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.5667. Min Act: -0.1700
Data Index: 3234905 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.5667. Min Act: -0.1700
Data Index: 4458311 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.5667. Min Act: -0.1700
Data Index: 225022 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.5667. Min Act: -0.1700
Data Index: 151243 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.5354. Min Act: -0.1700
Data Index: 251470 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7542. Min Range: -5.7542
Max Act: 5.5354. Min Act: -0.1700
Data Index: 397545 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19