Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6041 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.4273. Min Act: -0.1700
Data Index: 7248602 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.4097. Min Act: -0.1700
Data Index: 6225199 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3921. Min Act: -0.1700
Data Index: 8399684 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3921. Min Act: -0.1700
Data Index: 611860 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3921. Min Act: -0.1700
Data Index: 7838628 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3921. Min Act: -0.1700
Data Index: 4870464 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3921. Min Act: -0.1700
Data Index: 965148 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3921. Min Act: -0.1700
Data Index: 8527750 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3745. Min Act: -0.1700
Data Index: 4988343 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3745. Min Act: -0.1700
Data Index: 7847158 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3392. Min Act: -0.1700
Data Index: 3687000 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3569. Min Act: -0.1700
Data Index: 2547803 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3392. Min Act: -0.1700
Data Index: 6541040 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3392. Min Act: -0.1700
Data Index: 8552810 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3392. Min Act: -0.1700
Data Index: 6669338 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3392. Min Act: -0.1700
Data Index: 204138 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3392. Min Act: -0.1700
Data Index: 6253552 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3392. Min Act: -0.1700
Data Index: 6799621 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3392. Min Act: -0.1700
Data Index: 8158539 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4273. Min Range: -1.4273
Max Act: 1.3392. Min Act: -0.1700
Data Index: 2315216 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19