Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2754 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.7037. Min Act: -0.1700
Data Index: 4199196 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.5787. Min Act: -0.1700
Data Index: 8732473 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.5474. Min Act: -0.1700
Data Index: 2696513 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.3599. Min Act: -0.1700
Data Index: 3637870 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.2662. Min Act: -0.1700
Data Index: 7248220 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.2662. Min Act: -0.1700
Data Index: 4542108 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.2349. Min Act: -0.1700
Data Index: 6530627 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.2662. Min Act: -0.1700
Data Index: 5514666 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.1724. Min Act: -0.1700
Data Index: 6900775 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.1724. Min Act: -0.1700
Data Index: 5560811 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.1412. Min Act: -0.1700
Data Index: 8398294 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.1099. Min Act: -0.1700
Data Index: 675502 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.0787. Min Act: -0.1700
Data Index: 4611908 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.0162. Min Act: -0.1700
Data Index: 5731060 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.0162. Min Act: -0.1700
Data Index: 640859 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.0162. Min Act: -0.1700
Data Index: 6516399 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.0162. Min Act: -0.1700
Data Index: 8187803 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7037. Min Range: -5.7037
Max Act: 5.0162. Min Act: -0.1700
Data Index: 4756558 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7037. Min Range: -5.7037
Max Act: 4.9849. Min Act: -0.1700
Data Index: 28264 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7037. Min Range: -5.7037
Max Act: 4.9849. Min Act: -0.1700
Data Index: 4583347 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19