Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4896 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2603. Min Range: -5.2603
Max Act: 5.2603. Min Act: -0.1700
Data Index: 265135 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.8228. Min Act: -0.1700
Data Index: 6238043 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.6978. Min Act: -0.1700
Data Index: 5537018 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.6041. Min Act: -0.1700
Data Index: 4736262 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.6041. Min Act: -0.1700
Data Index: 20111 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.5728. Min Act: -0.1700
Data Index: 7800890 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.5728. Min Act: -0.1700
Data Index: 484024 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.5416. Min Act: -0.1700
Data Index: 3531317 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.5416. Min Act: -0.1700
Data Index: 7800889 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.5416. Min Act: -0.1700
Data Index: 5513168 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.5103. Min Act: -0.1700
Data Index: 802490 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.5103. Min Act: -0.1700
Data Index: 322201 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.4791. Min Act: -0.1700
Data Index: 5852311 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.4478. Min Act: -0.1700
Data Index: 5044489 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.4791. Min Act: -0.1700
Data Index: 6868895 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.4791. Min Act: -0.1700
Data Index: 2111211 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.4791. Min Act: -0.1700
Data Index: 3211064 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.4478. Min Act: -0.1700
Data Index: 4564434 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.4478. Min Act: -0.1700
Data Index: 7532736 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2603. Min Range: -5.2603
Max Act: 4.4478. Min Act: -0.1700
Data Index: 2988614 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19