Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2758 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5374. Min Range: -8.5374
Max Act: 8.5374. Min Act: -0.1700
Data Index: 6229106 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5374. Min Range: -8.5374
Max Act: 8.3187. Min Act: -0.1700
Data Index: 1972201 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5374. Min Range: -8.5374
Max Act: 8.2562. Min Act: -0.1700
Data Index: 2136687 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5374. Min Range: -8.5374
Max Act: 8.1624. Min Act: -0.1700
Data Index: 7088239 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5374. Min Range: -8.5374
Max Act: 8.0687. Min Act: -0.1700
Data Index: 1071827 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5374. Min Range: -8.5374
Max Act: 7.8812. Min Act: -0.1700
Data Index: 1839951 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5374. Min Range: -8.5374
Max Act: 7.8499. Min Act: -0.1700
Data Index: 1090028 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5374. Min Range: -8.5374
Max Act: 7.8812. Min Act: -0.1700
Data Index: 7024947 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5374. Min Range: -8.5374
Max Act: 7.8812. Min Act: -0.1700
Data Index: 1090021 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5374. Min Range: -8.5374
Max Act: 7.8499. Min Act: -0.1700
Data Index: 8516278 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5374. Min Range: -8.5374
Max Act: 7.8187. Min Act: -0.1700
Data Index: 8584388 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5374. Min Range: -8.5374
Max Act: 7.7874. Min Act: -0.1700
Data Index: 2625984 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5374. Min Range: -8.5374
Max Act: 7.8499. Min Act: -0.1700
Data Index: 8198691 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5374. Min Range: -8.5374
Max Act: 7.7874. Min Act: -0.1700
Data Index: 7083944 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5374. Min Range: -8.5374
Max Act: 7.7249. Min Act: -0.1700
Data Index: 2772346 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5374. Min Range: -8.5374
Max Act: 7.7874. Min Act: -0.1700
Data Index: 318120 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5374. Min Range: -8.5374
Max Act: 7.7249. Min Act: -0.1700
Data Index: 8522351 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5374. Min Range: -8.5374
Max Act: 7.6937. Min Act: -0.1700
Data Index: 3810316 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5374. Min Range: -8.5374
Max Act: 7.7249. Min Act: -0.1700
Data Index: 3503476 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5374. Min Range: -8.5374
Max Act: 7.5687. Min Act: -0.1700
Data Index: 1052957 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19