Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2937 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.7570. Min Act: -0.1700
Data Index: 1348944 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.6320. Min Act: -0.1700
Data Index: 2133907 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.6632. Min Act: -0.1700
Data Index: 7590152 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.6320. Min Act: -0.1700
Data Index: 4157773 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.6007. Min Act: -0.1700
Data Index: 6350279 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.6007. Min Act: -0.1700
Data Index: 8809034 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.5382. Min Act: -0.1700
Data Index: 7600646 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.5382. Min Act: -0.1700
Data Index: 1618873 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.5382. Min Act: -0.1700
Data Index: 5386148 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.5070. Min Act: -0.1700
Data Index: 1293518 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.4757. Min Act: -0.1700
Data Index: 2527239 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.4445. Min Act: -0.1700
Data Index: 8113736 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.4445. Min Act: -0.1700
Data Index: 2782354 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.4132. Min Act: -0.1700
Data Index: 6836750 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.4445. Min Act: -0.1700
Data Index: 8199490 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.3820. Min Act: -0.1700
Data Index: 6460813 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.3820. Min Act: -0.1700
Data Index: 5239820 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.3820. Min Act: -0.1700
Data Index: 441128 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.4132. Min Act: -0.1700
Data Index: 1633589 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7570. Min Range: -4.7570
Max Act: 4.4132. Min Act: -0.1700
Data Index: 5761886 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19