Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1041 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1391. Min Range: -4.1391
Max Act: 4.1391. Min Act: -0.1700
Data Index: 4329763 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1391. Min Range: -4.1391
Max Act: 4.0140. Min Act: -0.1700
Data Index: 3975740 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1391. Min Range: -4.1391
Max Act: 4.0140. Min Act: -0.1700
Data Index: 591411 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1391. Min Range: -4.1391
Max Act: 3.9515. Min Act: -0.1700
Data Index: 3823605 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1391. Min Range: -4.1391
Max Act: 3.9828. Min Act: -0.1700
Data Index: 3841628 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1391. Min Range: -4.1391
Max Act: 3.9515. Min Act: -0.1700
Data Index: 2999110 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1391. Min Range: -4.1391
Max Act: 3.9359. Min Act: -0.1700
Data Index: 7580305 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1391. Min Range: -4.1391
Max Act: 3.8890. Min Act: -0.1700
Data Index: 7968586 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1391. Min Range: -4.1391
Max Act: 3.8890. Min Act: -0.1700
Data Index: 1172333 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1391. Min Range: -4.1391
Max Act: 3.9046. Min Act: -0.1700
Data Index: 6306255 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1391. Min Range: -4.1391
Max Act: 3.8734. Min Act: -0.1700
Data Index: 1241032 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1391. Min Range: -4.1391
Max Act: 3.8890. Min Act: -0.1700
Data Index: 3714763 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1391. Min Range: -4.1391
Max Act: 3.8734. Min Act: -0.1700
Data Index: 485295 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1391. Min Range: -4.1391
Max Act: 3.8734. Min Act: -0.1700
Data Index: 1416880 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1391. Min Range: -4.1391
Max Act: 3.8577. Min Act: -0.1700
Data Index: 5724279 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1391. Min Range: -4.1391
Max Act: 3.8577. Min Act: -0.1700
Data Index: 5904829 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1391. Min Range: -4.1391
Max Act: 3.8734. Min Act: -0.1700
Data Index: 7624980 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1391. Min Range: -4.1391
Max Act: 3.8577. Min Act: -0.1700
Data Index: 58184 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1391. Min Range: -4.1391
Max Act: 3.8421. Min Act: -0.1700
Data Index: 648704 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1391. Min Range: -4.1391
Max Act: 3.8264. Min Act: -0.1700
Data Index: 1850509 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19