Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5744 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1729. Min Range: -8.1729
Max Act: 8.1729. Min Act: -0.1700
Data Index: 4551636 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.9854. Min Act: -0.1700
Data Index: 5539569 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.7979. Min Act: -0.1700
Data Index: 2695078 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.7666. Min Act: -0.1700
Data Index: 2811968 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.7979. Min Act: -0.1700
Data Index: 8378645 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.7041. Min Act: -0.1700
Data Index: 4002576 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.6729. Min Act: -0.1700
Data Index: 4069969 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.6104. Min Act: -0.1700
Data Index: 4702977 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.6104. Min Act: -0.1700
Data Index: 3465359 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.5479. Min Act: -0.1700
Data Index: 8418877 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.5479. Min Act: -0.1700
Data Index: 4998853 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.5479. Min Act: -0.1700
Data Index: 208711 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.5166. Min Act: -0.1700
Data Index: 7140322 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.5166. Min Act: -0.1700
Data Index: 5687011 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.4854. Min Act: -0.1700
Data Index: 5441342 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.4854. Min Act: -0.1700
Data Index: 589637 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.4229. Min Act: -0.1700
Data Index: 7015528 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.4541. Min Act: -0.1700
Data Index: 3973698 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.4541. Min Act: -0.1700
Data Index: 4010506 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1729. Min Range: -8.1729
Max Act: 7.4541. Min Act: -0.1700
Data Index: 7180127 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19