Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5182 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2335. Min Range: -6.2335
Max Act: 6.2335. Min Act: -0.1700
Data Index: 3931047 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2335. Min Range: -6.2335
Max Act: 6.2022. Min Act: -0.1700
Data Index: 2241091 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2335. Min Range: -6.2335
Max Act: 6.1085. Min Act: -0.1700
Data Index: 6141350 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2335. Min Range: -6.2335
Max Act: 6.0772. Min Act: -0.1700
Data Index: 6016299 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2335. Min Range: -6.2335
Max Act: 6.0460. Min Act: -0.1700
Data Index: 6683227 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2335. Min Range: -6.2335
Max Act: 6.0460. Min Act: -0.1700
Data Index: 2267009 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2335. Min Range: -6.2335
Max Act: 5.9210. Min Act: -0.1700
Data Index: 7708221 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2335. Min Range: -6.2335
Max Act: 5.9522. Min Act: -0.1700
Data Index: 914522 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2335. Min Range: -6.2335
Max Act: 5.9210. Min Act: -0.1700
Data Index: 6440656 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2335. Min Range: -6.2335
Max Act: 5.9522. Min Act: -0.1700
Data Index: 6280124 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2335. Min Range: -6.2335
Max Act: 5.8585. Min Act: -0.1700
Data Index: 1791538 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2335. Min Range: -6.2335
Max Act: 5.8585. Min Act: -0.1700
Data Index: 6418807 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2335. Min Range: -6.2335
Max Act: 5.8585. Min Act: -0.1700
Data Index: 4264321 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2335. Min Range: -6.2335
Max Act: 5.8272. Min Act: -0.1700
Data Index: 8428767 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2335. Min Range: -6.2335
Max Act: 5.8272. Min Act: -0.1700
Data Index: 8595353 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2335. Min Range: -6.2335
Max Act: 5.8272. Min Act: -0.1700
Data Index: 5840402 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2335. Min Range: -6.2335
Max Act: 5.7960. Min Act: -0.1700
Data Index: 4719659 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2335. Min Range: -6.2335
Max Act: 5.7960. Min Act: -0.1700
Data Index: 3715212 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2335. Min Range: -6.2335
Max Act: 5.7960. Min Act: -0.1700
Data Index: 3170394 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2335. Min Range: -6.2335
Max Act: 5.7960. Min Act: -0.1700
Data Index: 4458280 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19