Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2955 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.2249. Min Act: -0.1700
Data Index: 7078936 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.1305. Min Act: -0.1700
Data Index: 6931995 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.1148. Min Act: -0.1700
Data Index: 8578136 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.1148. Min Act: -0.1700
Data Index: 6763427 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.0990. Min Act: -0.1700
Data Index: 1138389 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.0990. Min Act: -0.1700
Data Index: 2230276 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.0990. Min Act: -0.1700
Data Index: 1070632 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.0990. Min Act: -0.1700
Data Index: 2397098 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.0832. Min Act: -0.1700
Data Index: 4364101 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.0832. Min Act: -0.1700
Data Index: 6810662 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.0832. Min Act: -0.1700
Data Index: 7051629 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.0832. Min Act: -0.1700
Data Index: 2416922 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.0832. Min Act: -0.1700
Data Index: 3667793 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.0832. Min Act: -0.1700
Data Index: 2689049 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.0832. Min Act: -0.1700
Data Index: 5270064 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.0675. Min Act: -0.1700
Data Index: 6044135 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.0675. Min Act: -0.1700
Data Index: 1594358 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.0675. Min Act: -0.1700
Data Index: 679012 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.0675. Min Act: -0.1700
Data Index: 7892522 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2249. Min Range: -3.2249
Max Act: 3.0675. Min Act: -0.1700
Data Index: 5101665 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19