Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3084 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0921. Min Range: -6.0921
Max Act: 6.0921. Min Act: -0.1700
Data Index: 6157319 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0921. Min Range: -6.0921
Max Act: 6.0296. Min Act: -0.1700
Data Index: 8439207 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0921. Min Range: -6.0921
Max Act: 6.0296. Min Act: -0.1700
Data Index: 2700112 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.9358. Min Act: -0.1700
Data Index: 3941493 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.9358. Min Act: -0.1700
Data Index: 1694525 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.9358. Min Act: -0.1700
Data Index: 8815832 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.9358. Min Act: -0.1700
Data Index: 2867199 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.9358. Min Act: -0.1700
Data Index: 7751269 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.9358. Min Act: -0.1700
Data Index: 6608886 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.9046. Min Act: -0.1700
Data Index: 2330515 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.9046. Min Act: -0.1700
Data Index: 4244690 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.9046. Min Act: -0.1700
Data Index: 1894636 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.8733. Min Act: -0.1700
Data Index: 5826183 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.9046. Min Act: -0.1700
Data Index: 5883162 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.9046. Min Act: -0.1700
Data Index: 4008003 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.9046. Min Act: -0.1700
Data Index: 7652003 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.9046. Min Act: -0.1700
Data Index: 1448018 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.9046. Min Act: -0.1700
Data Index: 6435615 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.8733. Min Act: -0.1700
Data Index: 1464067 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.8733. Min Act: -0.1700
Data Index: 1468420 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19