Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 846 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2452. Min Range: -4.2452
Max Act: 4.2452. Min Act: -0.1700
Data Index: 6182883 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2452. Min Range: -4.2452
Max Act: 4.1827. Min Act: -0.1700
Data Index: 7730657 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2452. Min Range: -4.2452
Max Act: 4.2140. Min Act: -0.1700
Data Index: 4344035 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2452. Min Range: -4.2452
Max Act: 4.2140. Min Act: -0.1700
Data Index: 25983 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2452. Min Range: -4.2452
Max Act: 4.1514. Min Act: -0.1700
Data Index: 4981265 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2452. Min Range: -4.2452
Max Act: 4.1514. Min Act: -0.1700
Data Index: 4160545 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2452. Min Range: -4.2452
Max Act: 4.1202. Min Act: -0.1700
Data Index: 6679194 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2452. Min Range: -4.2452
Max Act: 4.0577. Min Act: -0.1700
Data Index: 4779616 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2452. Min Range: -4.2452
Max Act: 4.0264. Min Act: -0.1700
Data Index: 5747492 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2452. Min Range: -4.2452
Max Act: 4.0264. Min Act: -0.1700
Data Index: 7497437 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2452. Min Range: -4.2452
Max Act: 4.0577. Min Act: -0.1700
Data Index: 3877938 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2452. Min Range: -4.2452
Max Act: 4.0264. Min Act: -0.1700
Data Index: 1193821 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2452. Min Range: -4.2452
Max Act: 4.0264. Min Act: -0.1700
Data Index: 2927557 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2452. Min Range: -4.2452
Max Act: 4.0264. Min Act: -0.1700
Data Index: 8285653 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2452. Min Range: -4.2452
Max Act: 3.9952. Min Act: -0.1700
Data Index: 2905172 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2452. Min Range: -4.2452
Max Act: 3.9639. Min Act: -0.1700
Data Index: 5476567 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2452. Min Range: -4.2452
Max Act: 3.9952. Min Act: -0.1700
Data Index: 1492579 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2452. Min Range: -4.2452
Max Act: 3.9639. Min Act: -0.1700
Data Index: 3875783 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2452. Min Range: -4.2452
Max Act: 3.9639. Min Act: -0.1700
Data Index: 2240960 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2452. Min Range: -4.2452
Max Act: 3.9639. Min Act: -0.1700
Data Index: 1353897 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19