Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4472 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0069. Min Range: -3.0069
Max Act: 3.0069. Min Act: -0.1586
Data Index: 6681126 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.7848. Min Act: -0.1700
Data Index: 4384098 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.7210. Min Act: -0.1700
Data Index: 8638224 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.7210. Min Act: -0.1700
Data Index: 4813925 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.7050. Min Act: -0.1700
Data Index: 1964766 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.7050. Min Act: -0.1593
Data Index: 4418283 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.6730. Min Act: -0.1700
Data Index: 4651101 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.6569. Min Act: -0.1700
Data Index: 7604642 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.6248. Min Act: -0.1685
Data Index: 4143664 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.6248. Min Act: -0.1700
Data Index: 2295110 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.6248. Min Act: -0.1699
Data Index: 5897949 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.6088. Min Act: -0.1699
Data Index: 3210223 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.6088. Min Act: -0.1669
Data Index: 3520330 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.5927. Min Act: -0.1675
Data Index: 3401917 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.5927. Min Act: -0.1666
Data Index: 621379 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.5927. Min Act: -0.1700
Data Index: 5806450 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.5927. Min Act: -0.1671
Data Index: 6590047 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.5927. Min Act: -0.1700
Data Index: 5708058 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.5927. Min Act: -0.1475
Data Index: 3323315 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0069. Min Range: -3.0069
Max Act: 2.5765. Min Act: -0.1700
Data Index: 1431894 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19