Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2452 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2703. Min Range: -5.2703
Max Act: 5.2703. Min Act: -0.1700
Data Index: 6102808 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2703. Min Range: -5.2703
Max Act: 5.1766. Min Act: -0.1700
Data Index: 344805 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2703. Min Range: -5.2703
Max Act: 5.1453. Min Act: -0.1700
Data Index: 241408 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2703. Min Range: -5.2703
Max Act: 5.1453. Min Act: -0.1700
Data Index: 667328 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2703. Min Range: -5.2703
Max Act: 5.1453. Min Act: -0.1700
Data Index: 241406 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2703. Min Range: -5.2703
Max Act: 5.1141. Min Act: -0.1700
Data Index: 8460 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2703. Min Range: -5.2703
Max Act: 5.0828. Min Act: -0.1700
Data Index: 417241 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2703. Min Range: -5.2703
Max Act: 5.0828. Min Act: -0.1700
Data Index: 1814716 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2703. Min Range: -5.2703
Max Act: 4.9891. Min Act: -0.1700
Data Index: 6621761 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2703. Min Range: -5.2703
Max Act: 4.9891. Min Act: -0.1700
Data Index: 2183598 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2703. Min Range: -5.2703
Max Act: 4.9578. Min Act: -0.1700
Data Index: 1850826 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2703. Min Range: -5.2703
Max Act: 4.9891. Min Act: -0.1700
Data Index: 7113637 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2703. Min Range: -5.2703
Max Act: 4.9578. Min Act: -0.1700
Data Index: 1319843 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2703. Min Range: -5.2703
Max Act: 4.9266. Min Act: -0.1700
Data Index: 4405725 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2703. Min Range: -5.2703
Max Act: 4.9266. Min Act: -0.1700
Data Index: 409270 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2703. Min Range: -5.2703
Max Act: 4.9266. Min Act: -0.1700
Data Index: 574446 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2703. Min Range: -5.2703
Max Act: 4.8953. Min Act: -0.1700
Data Index: 6325910 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2703. Min Range: -5.2703
Max Act: 4.8953. Min Act: -0.1700
Data Index: 5532130 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2703. Min Range: -5.2703
Max Act: 4.8641. Min Act: -0.1700
Data Index: 496021 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2703. Min Range: -5.2703
Max Act: 4.8953. Min Act: -0.1700
Data Index: 6491965 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19