Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4532 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.8025. Min Act: -0.1700
Data Index: 2524410 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.6150. Min Act: -0.1700
Data Index: 5370596 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.4900. Min Act: -0.1700
Data Index: 6570940 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.5213. Min Act: -0.1700
Data Index: 3401678 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.4900. Min Act: -0.1700
Data Index: 2010050 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.3650. Min Act: -0.1700
Data Index: 4692300 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.3650. Min Act: -0.1700
Data Index: 1788639 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.3650. Min Act: -0.1700
Data Index: 6555645 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.3650. Min Act: -0.1700
Data Index: 6715968 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.3338. Min Act: -0.1700
Data Index: 2020147 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.3338. Min Act: -0.1700
Data Index: 6565920 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.3338. Min Act: -0.1700
Data Index: 725217 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.3338. Min Act: -0.1700
Data Index: 365268 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.3025. Min Act: -0.1700
Data Index: 8422923 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.3025. Min Act: -0.1700
Data Index: 6715965 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.3025. Min Act: -0.1700
Data Index: 5291560 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.2713. Min Act: -0.1700
Data Index: 2688255 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.2400. Min Act: -0.1700
Data Index: 1823027 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.3025. Min Act: -0.1700
Data Index: 1061921 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8025. Min Range: -6.8025
Max Act: 6.2400. Min Act: -0.1700
Data Index: 740458 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19