Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3520 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0568. Min Range: -2.0568
Max Act: 2.0568. Min Act: -0.1700
Data Index: 1497606 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.9724. Min Act: -0.1700
Data Index: 1967445 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.9044. Min Act: -0.1700
Data Index: 6959361 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.8873. Min Act: -0.1700
Data Index: 4226590 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.8703. Min Act: -0.1700
Data Index: 3072461 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.8188. Min Act: -0.1700
Data Index: 5135108 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.8017. Min Act: -0.1700
Data Index: 2100892 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.8360. Min Act: -0.1700
Data Index: 6508588 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.8017. Min Act: -0.1700
Data Index: 4328922 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.8017. Min Act: -0.1700
Data Index: 7310114 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.8017. Min Act: -0.1700
Data Index: 1570287 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.8017. Min Act: -0.1700
Data Index: 3938825 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.7844. Min Act: -0.1700
Data Index: 628551 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.7672. Min Act: -0.1700
Data Index: 5030482 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.7672. Min Act: -0.1700
Data Index: 8274364 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.7499. Min Act: -0.1700
Data Index: 8274399 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.7672. Min Act: -0.1700
Data Index: 4793392 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.7672. Min Act: -0.1700
Data Index: 7447361 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.7499. Min Act: -0.1700
Data Index: 8162688 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0568. Min Range: -2.0568
Max Act: 1.7326. Min Act: -0.1700
Data Index: 6898851 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19