Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4286 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4142. Min Range: -9.4142
Max Act: 9.4142. Min Act: -0.1700
Data Index: 145207 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4142. Min Range: -9.4142
Max Act: 9.0392. Min Act: -0.1700
Data Index: 6172329 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.9142. Min Act: -0.1700
Data Index: 5592082 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.9142. Min Act: -0.1700
Data Index: 1270275 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.9767. Min Act: -0.1700
Data Index: 1356717 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.9142. Min Act: -0.1700
Data Index: 8410488 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.8517. Min Act: -0.1700
Data Index: 7891130 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.8517. Min Act: -0.1700
Data Index: 3946873 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.8517. Min Act: -0.1700
Data Index: 5487390 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.7892. Min Act: -0.1700
Data Index: 3178120 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.7267. Min Act: -0.1700
Data Index: 4529764 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.7267. Min Act: -0.1700
Data Index: 2790409 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.6017. Min Act: -0.1700
Data Index: 5092532 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.6642. Min Act: -0.1700
Data Index: 1366599 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.5392. Min Act: -0.1700
Data Index: 6374190 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.5392. Min Act: -0.1700
Data Index: 5538312 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.5392. Min Act: -0.1700
Data Index: 8111951 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.5392. Min Act: -0.1700
Data Index: 4076599 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.5392. Min Act: -0.1700
Data Index: 2283482 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4142. Min Range: -9.4142
Max Act: 8.4767. Min Act: -0.1700
Data Index: 7556295 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19