Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3016 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0303. Min Range: -2.0303
Max Act: 2.0303. Min Act: -0.1700
Data Index: 7412441 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0303. Min Range: -2.0303
Max Act: 2.0134. Min Act: -0.1700
Data Index: 3911287 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.9627. Min Act: -0.1700
Data Index: 1371820 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.9117. Min Act: -0.1700
Data Index: 6668032 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.9117. Min Act: -0.1700
Data Index: 2741031 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.9117. Min Act: -0.1700
Data Index: 4301667 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.8946. Min Act: -0.1700
Data Index: 5567709 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.8776. Min Act: -0.1700
Data Index: 1651560 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.8946. Min Act: -0.1700
Data Index: 1541652 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.8776. Min Act: -0.1700
Data Index: 2079564 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.8776. Min Act: -0.1700
Data Index: 470652 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.8776. Min Act: -0.1700
Data Index: 4716850 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.8605. Min Act: -0.1700
Data Index: 3381657 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.8776. Min Act: -0.1700
Data Index: 6571962 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.8605. Min Act: -0.1700
Data Index: 4649841 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.8605. Min Act: -0.1700
Data Index: 6025402 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.8605. Min Act: -0.1700
Data Index: 7397183 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.8605. Min Act: -0.1700
Data Index: 5053242 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.8605. Min Act: -0.1700
Data Index: 5095374 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0303. Min Range: -2.0303
Max Act: 1.8776. Min Act: -0.1700
Data Index: 5176964 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19