Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3047 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.5540. Min Act: -0.1700
Data Index: 6993326 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.2727. Min Act: -0.1700
Data Index: 8236009 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.2102. Min Act: -0.1700
Data Index: 6304532 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.1477. Min Act: -0.1700
Data Index: 14503 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.1477. Min Act: -0.1700
Data Index: 5277863 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.1477. Min Act: -0.1700
Data Index: 8352498 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.1477. Min Act: -0.1700
Data Index: 559432 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5540. Min Range: -6.5540
Max Act: 6.0540. Min Act: -0.1700
Data Index: 1203180 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5540. Min Range: -6.5540
Max Act: 5.9602. Min Act: -0.1700
Data Index: 5811744 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5540. Min Range: -6.5540
Max Act: 5.9290. Min Act: -0.1700
Data Index: 1996357 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5540. Min Range: -6.5540
Max Act: 5.9602. Min Act: -0.1700
Data Index: 3272917 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5540. Min Range: -6.5540
Max Act: 5.9290. Min Act: -0.1700
Data Index: 2346902 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5540. Min Range: -6.5540
Max Act: 5.8977. Min Act: -0.1700
Data Index: 591647 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5540. Min Range: -6.5540
Max Act: 5.8977. Min Act: -0.1700
Data Index: 679305 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5540. Min Range: -6.5540
Max Act: 5.8665. Min Act: -0.1700
Data Index: 3503397 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5540. Min Range: -6.5540
Max Act: 5.8665. Min Act: -0.1700
Data Index: 4181224 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5540. Min Range: -6.5540
Max Act: 5.8665. Min Act: -0.1700
Data Index: 4774426 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5540. Min Range: -6.5540
Max Act: 5.8665. Min Act: -0.1700
Data Index: 1929533 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5540. Min Range: -6.5540
Max Act: 5.8352. Min Act: -0.1700
Data Index: 1888113 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5540. Min Range: -6.5540
Max Act: 5.8665. Min Act: -0.1700
Data Index: 2978950 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19