Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5822 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8703. Min Range: -9.8703
Max Act: 9.8703. Min Act: -0.1700
Data Index: 248016 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8703. Min Range: -9.8703
Max Act: 9.4953. Min Act: -0.1700
Data Index: 248017 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8703. Min Range: -9.8703
Max Act: 9.1828. Min Act: -0.1700
Data Index: 6876841 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8703. Min Range: -9.8703
Max Act: 8.9953. Min Act: -0.1700
Data Index: 8021444 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8703. Min Range: -9.8703
Max Act: 8.9328. Min Act: -0.1700
Data Index: 3355260 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8703. Min Range: -9.8703
Max Act: 8.8078. Min Act: -0.1700
Data Index: 5472900 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8703. Min Range: -9.8703
Max Act: 8.8078. Min Act: -0.1700
Data Index: 4721734 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8703. Min Range: -9.8703
Max Act: 8.8703. Min Act: -0.1700
Data Index: 1202595 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8703. Min Range: -9.8703
Max Act: 8.6828. Min Act: -0.1700
Data Index: 4491449 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8703. Min Range: -9.8703
Max Act: 8.7453. Min Act: -0.1700
Data Index: 4181443 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8703. Min Range: -9.8703
Max Act: 8.7453. Min Act: -0.1700
Data Index: 2833993 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8703. Min Range: -9.8703
Max Act: 8.6828. Min Act: -0.1700
Data Index: 7180298 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8703. Min Range: -9.8703
Max Act: 8.6828. Min Act: -0.1700
Data Index: 1043536 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8703. Min Range: -9.8703
Max Act: 8.6828. Min Act: -0.1700
Data Index: 5269470 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8703. Min Range: -9.8703
Max Act: 8.6203. Min Act: -0.1700
Data Index: 1017492 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8703. Min Range: -9.8703
Max Act: 8.5578. Min Act: -0.1700
Data Index: 6974664 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8703. Min Range: -9.8703
Max Act: 8.5578. Min Act: -0.1700
Data Index: 4263368 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8703. Min Range: -9.8703
Max Act: 8.5578. Min Act: -0.1700
Data Index: 3547051 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8703. Min Range: -9.8703
Max Act: 8.5578. Min Act: -0.1700
Data Index: 5269472 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8703. Min Range: -9.8703
Max Act: 8.4953. Min Act: -0.1700
Data Index: 6048977 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19