Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3294 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.5609. Min Act: -0.1700
Data Index: 1541810 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.4984. Min Act: -0.1700
Data Index: 5748937 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.4984. Min Act: -0.1700
Data Index: 1784656 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.4984. Min Act: -0.1700
Data Index: 1094515 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.4672. Min Act: -0.1700
Data Index: 8185422 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.4672. Min Act: -0.1700
Data Index: 66600 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.4047. Min Act: -0.1700
Data Index: 5495834 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.4359. Min Act: -0.1700
Data Index: 2088801 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.4359. Min Act: -0.1700
Data Index: 4863890 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.4047. Min Act: -0.1700
Data Index: 2488412 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.4359. Min Act: -0.1700
Data Index: 6223233 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.4047. Min Act: -0.1700
Data Index: 3220424 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.4047. Min Act: -0.1700
Data Index: 5204973 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.4047. Min Act: -0.1700
Data Index: 1865424 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.3734. Min Act: -0.1700
Data Index: 2488850 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.3422. Min Act: -0.1700
Data Index: 728149 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.3734. Min Act: -0.1700
Data Index: 5884313 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.3734. Min Act: -0.1700
Data Index: 3194740 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.3734. Min Act: -0.1700
Data Index: 4367578 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5609. Min Range: -4.5609
Max Act: 4.3734. Min Act: -0.1700
Data Index: 889387 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19