Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 844 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.9857. Min Act: -0.1700
Data Index: 2116075 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.7670. Min Act: -0.1700
Data Index: 3440730 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.7045. Min Act: -0.1700
Data Index: 3688651 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.6420. Min Act: -0.1700
Data Index: 8238345 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.6420. Min Act: -0.1700
Data Index: 2287071 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.6420. Min Act: -0.1700
Data Index: 1995995 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.6420. Min Act: -0.1700
Data Index: 3188360 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.6107. Min Act: -0.1700
Data Index: 7034912 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.6420. Min Act: -0.1700
Data Index: 6288930 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.5795. Min Act: -0.1700
Data Index: 6679815 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.5795. Min Act: -0.1700
Data Index: 7373137 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.5482. Min Act: -0.1700
Data Index: 6956582 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.5482. Min Act: -0.1700
Data Index: 3255399 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.5170. Min Act: -0.1700
Data Index: 2132549 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.5482. Min Act: -0.1700
Data Index: 4674671 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.5170. Min Act: -0.1700
Data Index: 6441928 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.5170. Min Act: -0.1700
Data Index: 232982 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.5170. Min Act: -0.1700
Data Index: 7444616 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.5170. Min Act: -0.1700
Data Index: 4112537 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9857. Min Range: -4.9857
Max Act: 4.4857. Min Act: -0.1700
Data Index: 6636091 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19