Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.8215. Min Act: -0.1700
Data Index: 8376856 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.6965. Min Act: -0.1700
Data Index: 502385 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.6028. Min Act: -0.1700
Data Index: 1606564 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.5403. Min Act: -0.1700
Data Index: 8116001 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.5403. Min Act: -0.1700
Data Index: 6871480 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.5403. Min Act: -0.1700
Data Index: 6280424 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.5090. Min Act: -0.1700
Data Index: 1047322 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.5090. Min Act: -0.1700
Data Index: 8164507 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.5090. Min Act: -0.1700
Data Index: 1246395 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.4465. Min Act: -0.1700
Data Index: 8606289 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.4778. Min Act: -0.1700
Data Index: 3422944 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.4465. Min Act: -0.1700
Data Index: 7588401 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.4465. Min Act: -0.1700
Data Index: 3010396 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.4465. Min Act: -0.1700
Data Index: 6134008 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.4465. Min Act: -0.1700
Data Index: 6597509 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.4465. Min Act: -0.1700
Data Index: 948233 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.4465. Min Act: -0.1700
Data Index: 8830184 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.4153. Min Act: -0.1700
Data Index: 6643812 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.4153. Min Act: -0.1700
Data Index: 2848850 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8215. Min Range: -7.8215
Max Act: 7.3840. Min Act: -0.1700
Data Index: 6716597 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19