Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1801. Min Range: -4.1801
Max Act: 4.1801. Min Act: -0.1700
Data Index: 4026003 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1801. Min Range: -4.1801
Max Act: 4.1801. Min Act: -0.1700
Data Index: 8745856 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1801. Min Range: -4.1801
Max Act: 4.1176. Min Act: -0.1700
Data Index: 8312266 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1801. Min Range: -4.1801
Max Act: 4.0863. Min Act: -0.1700
Data Index: 5841342 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1801. Min Range: -4.1801
Max Act: 4.0550. Min Act: -0.1700
Data Index: 7333255 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1801. Min Range: -4.1801
Max Act: 4.0550. Min Act: -0.1700
Data Index: 1053255 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1801. Min Range: -4.1801
Max Act: 4.0238. Min Act: -0.1700
Data Index: 3274149 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1801. Min Range: -4.1801
Max Act: 4.0238. Min Act: -0.1700
Data Index: 3018875 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1801. Min Range: -4.1801
Max Act: 4.0550. Min Act: -0.1700
Data Index: 969535 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1801. Min Range: -4.1801
Max Act: 3.9925. Min Act: -0.1700
Data Index: 3819775 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1801. Min Range: -4.1801
Max Act: 4.0238. Min Act: -0.1700
Data Index: 2623134 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1801. Min Range: -4.1801
Max Act: 4.0238. Min Act: -0.1700
Data Index: 6909431 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1801. Min Range: -4.1801
Max Act: 4.0238. Min Act: -0.1700
Data Index: 662533 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1801. Min Range: -4.1801
Max Act: 3.9925. Min Act: -0.1700
Data Index: 1337445 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1801. Min Range: -4.1801
Max Act: 3.9925. Min Act: -0.1700
Data Index: 5010254 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1801. Min Range: -4.1801
Max Act: 3.9925. Min Act: -0.1700
Data Index: 6907686 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1801. Min Range: -4.1801
Max Act: 3.9925. Min Act: -0.1700
Data Index: 4953931 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1801. Min Range: -4.1801
Max Act: 3.9925. Min Act: -0.1700
Data Index: 363801 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1801. Min Range: -4.1801
Max Act: 3.9925. Min Act: -0.1700
Data Index: 2364711 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1801. Min Range: -4.1801
Max Act: 3.9925. Min Act: -0.1700
Data Index: 6919634 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19