Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4214 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.9294. Min Act: -0.1700
Data Index: 5877903 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.8982. Min Act: -0.1700
Data Index: 6189102 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.8357. Min Act: -0.1700
Data Index: 5827758 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.8357. Min Act: -0.1700
Data Index: 6568316 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.8044. Min Act: -0.1700
Data Index: 1849007 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.7732. Min Act: -0.1700
Data Index: 1651350 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.7732. Min Act: -0.1700
Data Index: 142496 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.7419. Min Act: -0.1700
Data Index: 3112392 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.7419. Min Act: -0.1700
Data Index: 3392199 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.7107. Min Act: -0.1700
Data Index: 7019727 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.7107. Min Act: -0.1700
Data Index: 2230997 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.7107. Min Act: -0.1700
Data Index: 490395 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.6482. Min Act: -0.1700
Data Index: 6649200 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.6794. Min Act: -0.1700
Data Index: 3611052 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.6794. Min Act: -0.1700
Data Index: 8828024 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.6794. Min Act: -0.1700
Data Index: 5028870 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.6482. Min Act: -0.1700
Data Index: 1509752 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.6169. Min Act: -0.1700
Data Index: 6349492 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.5544. Min Act: -0.1700
Data Index: 3248461 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9294. Min Range: -5.9294
Max Act: 5.5857. Min Act: -0.1700
Data Index: 6305544 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19