Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3730 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.7065. Min Act: -0.1700
Data Index: 1734577 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.6891. Min Act: -0.1700
Data Index: 4718154 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.6891. Min Act: -0.1700
Data Index: 1162227 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.6544. Min Act: -0.1700
Data Index: 5550190 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.6370. Min Act: -0.1700
Data Index: 8094051 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.6370. Min Act: -0.1700
Data Index: 1476357 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.6195. Min Act: -0.1700
Data Index: 6999594 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.6021. Min Act: -0.1700
Data Index: 4730485 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.6021. Min Act: -0.1700
Data Index: 6701398 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.5846. Min Act: -0.1698
Data Index: 3054565 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.5846. Min Act: -0.1700
Data Index: 6300734 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.5846. Min Act: -0.1700
Data Index: 6996303 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.5846. Min Act: -0.1700
Data Index: 3025856 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.5671. Min Act: -0.1700
Data Index: 1959378 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.5846. Min Act: -0.1700
Data Index: 2191494 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.5671. Min Act: -0.1700
Data Index: 8678892 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.5671. Min Act: -0.1700
Data Index: 2696370 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.5671. Min Act: -0.1700
Data Index: 7616215 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.5496. Min Act: -0.1700
Data Index: 4015429 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7065. Min Range: -1.7065
Max Act: 1.5496. Min Act: -0.1697
Data Index: 7632537 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19