Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3674 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.6763. Min Act: -0.1700
Data Index: 5344380 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.5513. Min Act: -0.1700
Data Index: 657271 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.5201. Min Act: -0.1700
Data Index: 2624626 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.4888. Min Act: -0.1700
Data Index: 4258076 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.4576. Min Act: -0.1700
Data Index: 675888 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.3951. Min Act: -0.1700
Data Index: 656549 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.3326. Min Act: -0.1700
Data Index: 609814 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.3013. Min Act: -0.1700
Data Index: 6651173 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.3013. Min Act: -0.1700
Data Index: 4976889 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.2701. Min Act: -0.1700
Data Index: 6618088 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.2701. Min Act: -0.1700
Data Index: 3086316 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.2076. Min Act: -0.1700
Data Index: 2494197 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.1763. Min Act: -0.1700
Data Index: 3021347 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.1763. Min Act: -0.1700
Data Index: 3064441 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.1763. Min Act: -0.1700
Data Index: 7548857 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.1451. Min Act: -0.1700
Data Index: 1537865 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.1138. Min Act: -0.1700
Data Index: 1183382 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.1451. Min Act: -0.1700
Data Index: 1869472 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.1138. Min Act: -0.1700
Data Index: 4323816 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6763. Min Range: -6.6763
Max Act: 6.1451. Min Act: -0.1700
Data Index: 7285125 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19