Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4447 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.5474. Min Act: -0.1700
Data Index: 693268 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.4224. Min Act: -0.1700
Data Index: 1296784 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.3599. Min Act: -0.1700
Data Index: 4352339 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.2661. Min Act: -0.1700
Data Index: 4352338 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.2349. Min Act: -0.1700
Data Index: 4973348 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.2349. Min Act: -0.1700
Data Index: 5301732 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.2349. Min Act: -0.1700
Data Index: 5029443 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.1724. Min Act: -0.1700
Data Index: 7521650 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.1724. Min Act: -0.1700
Data Index: 3461675 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.1411. Min Act: -0.1700
Data Index: 5243702 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.1724. Min Act: -0.1700
Data Index: 5203959 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.1411. Min Act: -0.1700
Data Index: 5822747 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.1099. Min Act: -0.1700
Data Index: 1054858 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.0786. Min Act: -0.1700
Data Index: 5673604 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.0474. Min Act: -0.1700
Data Index: 6417486 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.0474. Min Act: -0.1700
Data Index: 7046846 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.0474. Min Act: -0.1700
Data Index: 1531399 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5474. Min Range: -7.5474
Max Act: 7.0474. Min Act: -0.1700
Data Index: 1192546 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5474. Min Range: -7.5474
Max Act: 6.9849. Min Act: -0.1700
Data Index: 1588283 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5474. Min Range: -7.5474
Max Act: 6.9536. Min Act: -0.1700
Data Index: 6911132 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19