Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1479 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0897. Min Range: -6.0897
Max Act: 6.0897. Min Act: -0.1700
Data Index: 1294201 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0897. Min Range: -6.0897
Max Act: 6.0272. Min Act: -0.1700
Data Index: 8425121 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.9960. Min Act: -0.1700
Data Index: 8822570 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.9647. Min Act: -0.1700
Data Index: 4677524 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.9335. Min Act: -0.1700
Data Index: 5813993 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.9022. Min Act: -0.1700
Data Index: 107560 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.8710. Min Act: -0.1700
Data Index: 851666 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.8710. Min Act: -0.1700
Data Index: 7479801 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.8710. Min Act: -0.1700
Data Index: 8301394 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.8397. Min Act: -0.1700
Data Index: 986065 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.8397. Min Act: -0.1700
Data Index: 4967127 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.8397. Min Act: -0.1700
Data Index: 4125451 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.8085. Min Act: -0.1700
Data Index: 7277107 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.7772. Min Act: -0.1700
Data Index: 1253307 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.7772. Min Act: -0.1700
Data Index: 6527814 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.7772. Min Act: -0.1700
Data Index: 4104908 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.7460. Min Act: -0.1700
Data Index: 4240986 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.7147. Min Act: -0.1700
Data Index: 495827 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.7147. Min Act: -0.1700
Data Index: 563088 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0897. Min Range: -6.0897
Max Act: 5.6835. Min Act: -0.1700
Data Index: 8402060 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19