Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6139 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.8113. Min Act: -0.1700
Data Index: 5216378 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.6863. Min Act: -0.1700
Data Index: 2381943 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5926. Min Act: -0.1700
Data Index: 4737915 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.6238. Min Act: -0.1700
Data Index: 3797023 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.6238. Min Act: -0.1700
Data Index: 6090267 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5926. Min Act: -0.1700
Data Index: 7296324 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5926. Min Act: -0.1699
Data Index: 3626201 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5926. Min Act: -0.1700
Data Index: 5218160 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5613. Min Act: -0.1700
Data Index: 1547501 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5613. Min Act: -0.1700
Data Index: 6997024 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5301. Min Act: -0.1700
Data Index: 5866350 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5613. Min Act: -0.1700
Data Index: 2390263 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5301. Min Act: -0.1700
Data Index: 4940045 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5613. Min Act: -0.1700
Data Index: 2213055 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5301. Min Act: -0.1700
Data Index: 3698176 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5301. Min Act: -0.1700
Data Index: 2972129 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5301. Min Act: -0.1700
Data Index: 6108464 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5301. Min Act: -0.1700
Data Index: 3657136 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5301. Min Act: -0.1700
Data Index: 3288186 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8113. Min Range: -5.8113
Max Act: 5.5301. Min Act: -0.1700
Data Index: 4378902 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19