Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2021. Min Range: -6.2021
Max Act: 6.2021. Min Act: -0.1700
Data Index: 3516379 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2021. Min Range: -6.2021
Max Act: 6.1396. Min Act: -0.1700
Data Index: 7783179 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2021. Min Range: -6.2021
Max Act: 6.1708. Min Act: -0.1700
Data Index: 17518 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2021. Min Range: -6.2021
Max Act: 6.1083. Min Act: -0.1700
Data Index: 17517 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2021. Min Range: -6.2021
Max Act: 5.6708. Min Act: -0.1700
Data Index: 7534213 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2021. Min Range: -6.2021
Max Act: 5.6396. Min Act: -0.1700
Data Index: 6466061 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2021. Min Range: -6.2021
Max Act: 5.6083. Min Act: -0.1700
Data Index: 7803347 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2021. Min Range: -6.2021
Max Act: 5.6083. Min Act: -0.1700
Data Index: 7599476 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2021. Min Range: -6.2021
Max Act: 5.6083. Min Act: -0.1700
Data Index: 8320244 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2021. Min Range: -6.2021
Max Act: 5.5771. Min Act: -0.1700
Data Index: 4378961 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2021. Min Range: -6.2021
Max Act: 5.5771. Min Act: -0.1700
Data Index: 7599473 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2021. Min Range: -6.2021
Max Act: 5.5458. Min Act: -0.1700
Data Index: 2044991 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2021. Min Range: -6.2021
Max Act: 5.5458. Min Act: -0.1700
Data Index: 7940787 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2021. Min Range: -6.2021
Max Act: 5.5146. Min Act: -0.1700
Data Index: 7680185 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2021. Min Range: -6.2021
Max Act: 5.5146. Min Act: -0.1700
Data Index: 499311 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2021. Min Range: -6.2021
Max Act: 5.5146. Min Act: -0.1700
Data Index: 7313667 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2021. Min Range: -6.2021
Max Act: 5.5146. Min Act: -0.1700
Data Index: 6533502 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2021. Min Range: -6.2021
Max Act: 5.4833. Min Act: -0.1700
Data Index: 4270033 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2021. Min Range: -6.2021
Max Act: 5.4833. Min Act: -0.1700
Data Index: 5343234 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2021. Min Range: -6.2021
Max Act: 5.4521. Min Act: -0.1700
Data Index: 4363491 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19