Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2114 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2200. Min Range: -8.2200
Max Act: 8.2200. Min Act: -0.1700
Data Index: 906331 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.9075. Min Act: -0.1700
Data Index: 695144 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.8450. Min Act: -0.1700
Data Index: 6971589 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.8450. Min Act: -0.1700
Data Index: 6121081 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.6575. Min Act: -0.1700
Data Index: 505257 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.6575. Min Act: -0.1700
Data Index: 5762212 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.6575. Min Act: -0.1700
Data Index: 59893 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.5950. Min Act: -0.1700
Data Index: 402822 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.5950. Min Act: -0.1700
Data Index: 3813832 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.5950. Min Act: -0.1700
Data Index: 3805050 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.5950. Min Act: -0.1700
Data Index: 4748388 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.5325. Min Act: -0.1700
Data Index: 7316656 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.5325. Min Act: -0.1700
Data Index: 4302053 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.4700. Min Act: -0.1700
Data Index: 7478479 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.4700. Min Act: -0.1700
Data Index: 736639 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.4700. Min Act: -0.1700
Data Index: 4093658 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.4075. Min Act: -0.1700
Data Index: 4345809 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.4075. Min Act: -0.1700
Data Index: 8758844 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.4700. Min Act: -0.1700
Data Index: 6143837 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2200. Min Range: -8.2200
Max Act: 7.3450. Min Act: -0.1700
Data Index: 2411017 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19