Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 719 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.4506. Min Act: -0.1700
Data Index: 7448212 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.3256. Min Act: -0.1700
Data Index: 2587297 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.2631. Min Act: -0.1700
Data Index: 8764 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.2631. Min Act: -0.1700
Data Index: 3523515 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.2631. Min Act: -0.1700
Data Index: 3841213 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.2006. Min Act: -0.1700
Data Index: 104127 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.1381. Min Act: -0.1700
Data Index: 6174378 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.1381. Min Act: -0.1700
Data Index: 7472824 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.0756. Min Act: -0.1700
Data Index: 3025793 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.0756. Min Act: -0.1700
Data Index: 1259325 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.0756. Min Act: -0.1700
Data Index: 1523031 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.0131. Min Act: -0.1700
Data Index: 8692725 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.0131. Min Act: -0.1700
Data Index: 1099167 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.0131. Min Act: -0.1700
Data Index: 5492379 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.0131. Min Act: -0.1700
Data Index: 4516450 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.0131. Min Act: -0.1700
Data Index: 4399496 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.0131. Min Act: -0.1700
Data Index: 5307748 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.0131. Min Act: -0.1700
Data Index: 2564227 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4506. Min Range: -8.4506
Max Act: 8.0131. Min Act: -0.1700
Data Index: 1162376 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4506. Min Range: -8.4506
Max Act: 7.9506. Min Act: -0.1700
Data Index: 4058005 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19