Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3127 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4551. Min Range: -4.4551
Max Act: 4.4551. Min Act: -0.1700
Data Index: 743968 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4551. Min Range: -4.4551
Max Act: 4.1113. Min Act: -0.1700
Data Index: 8374593 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4551. Min Range: -4.4551
Max Act: 4.0175. Min Act: -0.1700
Data Index: 4241580 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4551. Min Range: -4.4551
Max Act: 3.9550. Min Act: -0.1700
Data Index: 810593 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4551. Min Range: -4.4551
Max Act: 3.8924. Min Act: -0.1700
Data Index: 743936 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4551. Min Range: -4.4551
Max Act: 3.8299. Min Act: -0.1700
Data Index: 2801281 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4551. Min Range: -4.4551
Max Act: 3.7986. Min Act: -0.1700
Data Index: 7722163 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4551. Min Range: -4.4551
Max Act: 3.8299. Min Act: -0.1700
Data Index: 3442500 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4551. Min Range: -4.4551
Max Act: 3.7986. Min Act: -0.1700
Data Index: 4459912 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4551. Min Range: -4.4551
Max Act: 3.7986. Min Act: -0.1700
Data Index: 640634 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4551. Min Range: -4.4551
Max Act: 3.7674. Min Act: -0.1700
Data Index: 5747318 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4551. Min Range: -4.4551
Max Act: 3.7674. Min Act: -0.1700
Data Index: 3591046 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4551. Min Range: -4.4551
Max Act: 3.7361. Min Act: -0.1700
Data Index: 6555213 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4551. Min Range: -4.4551
Max Act: 3.7361. Min Act: -0.1700
Data Index: 8773683 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4551. Min Range: -4.4551
Max Act: 3.7361. Min Act: -0.1700
Data Index: 2681978 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4551. Min Range: -4.4551
Max Act: 3.7048. Min Act: -0.1700
Data Index: 5526451 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4551. Min Range: -4.4551
Max Act: 3.7361. Min Act: -0.1700
Data Index: 1914909 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4551. Min Range: -4.4551
Max Act: 3.6735. Min Act: -0.1700
Data Index: 8228285 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4551. Min Range: -4.4551
Max Act: 3.6735. Min Act: -0.1700
Data Index: 6918304 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4551. Min Range: -4.4551
Max Act: 3.7048. Min Act: -0.1700
Data Index: 1986623 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19