Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2959 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.4551. Min Act: -0.1700
Data Index: 2753701 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.4551. Min Act: -0.1700
Data Index: 2181597 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.4238. Min Act: -0.1700
Data Index: 349913 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.4238. Min Act: -0.1700
Data Index: 855532 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.3613. Min Act: -0.1700
Data Index: 969100 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.3301. Min Act: -0.1700
Data Index: 7035105 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.3613. Min Act: -0.1700
Data Index: 3877973 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.2988. Min Act: -0.1699
Data Index: 3946731 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.2988. Min Act: -0.1700
Data Index: 6705088 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.2988. Min Act: -0.1700
Data Index: 3518016 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.2988. Min Act: -0.1700
Data Index: 1998682 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.2676. Min Act: -0.1700
Data Index: 487613 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.2676. Min Act: -0.1700
Data Index: 8617926 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.2676. Min Act: -0.1700
Data Index: 1096427 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.2676. Min Act: -0.1700
Data Index: 7684649 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.2676. Min Act: -0.1700
Data Index: 5879934 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.2363. Min Act: -0.1700
Data Index: 4475189 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.2363. Min Act: -0.1700
Data Index: 7873141 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.2051. Min Act: -0.1700
Data Index: 4998744 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4551. Min Range: -6.4551
Max Act: 6.2051. Min Act: -0.1700
Data Index: 3413156 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19