Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2871 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1811. Min Range: -6.1811
Max Act: 6.1811. Min Act: -0.1700
Data Index: 4907257 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1811. Min Range: -6.1811
Max Act: 6.0561. Min Act: -0.1700
Data Index: 892518 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1811. Min Range: -6.1811
Max Act: 6.0561. Min Act: -0.1700
Data Index: 6865197 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1811. Min Range: -6.1811
Max Act: 6.0249. Min Act: -0.1700
Data Index: 586887 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1811. Min Range: -6.1811
Max Act: 5.9936. Min Act: -0.1700
Data Index: 565280 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1811. Min Range: -6.1811
Max Act: 5.9936. Min Act: -0.1700
Data Index: 4047474 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1811. Min Range: -6.1811
Max Act: 5.8686. Min Act: -0.1700
Data Index: 6857083 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1811. Min Range: -6.1811
Max Act: 5.8686. Min Act: -0.1700
Data Index: 7451594 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1811. Min Range: -6.1811
Max Act: 5.7749. Min Act: -0.1700
Data Index: 3309428 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1811. Min Range: -6.1811
Max Act: 5.6811. Min Act: -0.1700
Data Index: 1393823 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1811. Min Range: -6.1811
Max Act: 5.6811. Min Act: -0.1700
Data Index: 5220195 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1811. Min Range: -6.1811
Max Act: 5.6499. Min Act: -0.1700
Data Index: 6831597 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1811. Min Range: -6.1811
Max Act: 5.6811. Min Act: -0.1700
Data Index: 2575166 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1811. Min Range: -6.1811
Max Act: 5.6499. Min Act: -0.1700
Data Index: 7149340 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1811. Min Range: -6.1811
Max Act: 5.6186. Min Act: -0.1700
Data Index: 2196284 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1811. Min Range: -6.1811
Max Act: 5.6499. Min Act: -0.1700
Data Index: 2167180 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1811. Min Range: -6.1811
Max Act: 5.6499. Min Act: -0.1700
Data Index: 6667934 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1811. Min Range: -6.1811
Max Act: 5.6186. Min Act: -0.1700
Data Index: 4535267 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1811. Min Range: -6.1811
Max Act: 5.5874. Min Act: -0.1700
Data Index: 1709173 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1811. Min Range: -6.1811
Max Act: 5.5874. Min Act: -0.1700
Data Index: 8508959 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19