Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3813 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.6414. Min Act: -0.1700
Data Index: 5523164 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.6570. Min Act: -0.1700
Data Index: 4718139 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.5631. Min Act: -0.1700
Data Index: 4371372 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.5788. Min Act: -0.1700
Data Index: 3162853 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.5162. Min Act: -0.1700
Data Index: 6721602 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.4848. Min Act: -0.1700
Data Index: 697507 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.4378. Min Act: -0.1700
Data Index: 8080790 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.4065. Min Act: -0.1700
Data Index: 6782963 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.4222. Min Act: -0.1700
Data Index: 2871816 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.3908. Min Act: -0.1700
Data Index: 5142927 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.3751. Min Act: -0.1700
Data Index: 624402 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.3908. Min Act: -0.1700
Data Index: 4300543 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.3751. Min Act: -0.1700
Data Index: 830832 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.3437. Min Act: -0.1700
Data Index: 7114630 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.3751. Min Act: -0.1700
Data Index: 3807594 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.3437. Min Act: -0.1700
Data Index: 8016172 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.3594. Min Act: -0.1700
Data Index: 7367568 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.3281. Min Act: -0.1700
Data Index: 7303618 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.3281. Min Act: -0.1700
Data Index: 6728071 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6570. Min Range: -3.6570
Max Act: 3.3437. Min Act: -0.1700
Data Index: 1162686 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19