Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5488 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.5662. Min Act: -0.1700
Data Index: 3972677 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.4725. Min Act: -0.1700
Data Index: 8114684 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2850. Min Act: -0.1700
Data Index: 6632157 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.1912. Min Act: -0.1700
Data Index: 6099673 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.0975. Min Act: -0.1700
Data Index: 7794231 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.0975. Min Act: -0.1700
Data Index: 3195507 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.0350. Min Act: -0.1700
Data Index: 6322517 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.0037. Min Act: -0.1700
Data Index: 7073598 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.9725. Min Act: -0.1700
Data Index: 6162992 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.8787. Min Act: -0.1700
Data Index: 3046407 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.8787. Min Act: -0.1700
Data Index: 8447315 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.8162. Min Act: -0.1700
Data Index: 7096424 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.8787. Min Act: -0.1700
Data Index: 2369696 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.8475. Min Act: -0.1700
Data Index: 6386222 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.8475. Min Act: -0.1700
Data Index: 1199393 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.8162. Min Act: -0.1700
Data Index: 7365845 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.8162. Min Act: -0.1700
Data Index: 4030062 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.8162. Min Act: -0.1700
Data Index: 8594818 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.8162. Min Act: -0.1700
Data Index: 2628759 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.7850. Min Act: -0.1700
Data Index: 5993731 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19