Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1634 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.3689. Min Act: -0.1700
Data Index: 7341660 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.3064. Min Act: -0.1700
Data Index: 2510986 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.3064. Min Act: -0.1700
Data Index: 957594 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.3064. Min Act: -0.1700
Data Index: 4778026 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.2439. Min Act: -0.1700
Data Index: 3793726 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.2126. Min Act: -0.1700
Data Index: 2580808 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.2126. Min Act: -0.1700
Data Index: 8081965 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.1814. Min Act: -0.1700
Data Index: 3446545 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.1814. Min Act: -0.1700
Data Index: 6034928 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.1188. Min Act: -0.1700
Data Index: 957593 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.1814. Min Act: -0.1700
Data Index: 7057402 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.1501. Min Act: -0.1700
Data Index: 903209 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.1501. Min Act: -0.1700
Data Index: 4486634 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.1501. Min Act: -0.1700
Data Index: 8643960 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.1188. Min Act: -0.1700
Data Index: 3060665 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.1188. Min Act: -0.1700
Data Index: 6777323 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.1501. Min Act: -0.1700
Data Index: 6729252 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.1501. Min Act: -0.1700
Data Index: 6574851 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.1501. Min Act: -0.1700
Data Index: 2745620 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3689. Min Range: -4.3689
Max Act: 4.1501. Min Act: -0.1700
Data Index: 1215016 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19