Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 895 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.8078. Min Act: -0.1700
Data Index: 1339506 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.8391. Min Act: -0.1700
Data Index: 89043 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.7766. Min Act: -0.1700
Data Index: 22375 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.7766. Min Act: -0.1700
Data Index: 7929846 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.7766. Min Act: -0.1700
Data Index: 5281954 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.7141. Min Act: -0.1700
Data Index: 5635314 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.7141. Min Act: -0.1700
Data Index: 5538707 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.6828. Min Act: -0.1700
Data Index: 1035353 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.6516. Min Act: -0.1700
Data Index: 3710436 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.6828. Min Act: -0.1700
Data Index: 6953630 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.6516. Min Act: -0.1700
Data Index: 1080514 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.6203. Min Act: -0.1700
Data Index: 5603525 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.6516. Min Act: -0.1700
Data Index: 7039296 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.6516. Min Act: -0.1700
Data Index: 3469287 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.5891. Min Act: -0.1700
Data Index: 3196483 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.5891. Min Act: -0.1700
Data Index: 8598058 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.5891. Min Act: -0.1700
Data Index: 4615289 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.5266. Min Act: -0.1700
Data Index: 7769416 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.5578. Min Act: -0.1700
Data Index: 192588 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8391. Min Range: -4.8391
Max Act: 4.5578. Min Act: -0.1700
Data Index: 7769421 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19