Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3884 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.6349. Min Act: -0.1700
Data Index: 7412219 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.5724. Min Act: -0.1700
Data Index: 2059553 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.5099. Min Act: -0.1700
Data Index: 8230050 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.5099. Min Act: -0.1700
Data Index: 7570556 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.5099. Min Act: -0.1700
Data Index: 3466363 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.5099. Min Act: -0.1700
Data Index: 5724360 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.4787. Min Act: -0.1700
Data Index: 2609120 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.4787. Min Act: -0.1700
Data Index: 8558843 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.4474. Min Act: -0.1700
Data Index: 1548491 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.4787. Min Act: -0.1700
Data Index: 710592 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.4474. Min Act: -0.1700
Data Index: 5318672 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.4162. Min Act: -0.1700
Data Index: 3041090 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.4474. Min Act: -0.1700
Data Index: 3922960 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.4474. Min Act: -0.1700
Data Index: 7160395 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.4474. Min Act: -0.1700
Data Index: 2839523 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.4474. Min Act: -0.1700
Data Index: 7026328 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.4162. Min Act: -0.1700
Data Index: 787510 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.4162. Min Act: -0.1700
Data Index: 2887820 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.4162. Min Act: -0.1700
Data Index: 3506133 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6349. Min Range: -5.6349
Max Act: 5.3849. Min Act: -0.1700
Data Index: 3702220 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19