Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.9716. Min Act: -0.1700
Data Index: 4707044 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.6591. Min Act: -0.1700
Data Index: 3105922 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.6591. Min Act: -0.1700
Data Index: 6395269 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.5653. Min Act: -0.1700
Data Index: 8545859 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.5028. Min Act: -0.1700
Data Index: 2382279 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.4716. Min Act: -0.1700
Data Index: 5376197 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.4716. Min Act: -0.1700
Data Index: 6420518 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.4403. Min Act: -0.1700
Data Index: 5171670 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.4716. Min Act: -0.1700
Data Index: 8557223 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.4403. Min Act: -0.1700
Data Index: 8790576 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.3778. Min Act: -0.1700
Data Index: 1793479 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.3778. Min Act: -0.1700
Data Index: 8002202 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.3466. Min Act: -0.1700
Data Index: 595522 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.4091. Min Act: -0.1700
Data Index: 553528 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.3466. Min Act: -0.1700
Data Index: 2940194 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.3778. Min Act: -0.1700
Data Index: 6647775 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.3466. Min Act: -0.1700
Data Index: 8493738 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.3466. Min Act: -0.1700
Data Index: 6919840 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.3466. Min Act: -0.1700
Data Index: 7462562 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9716. Min Range: -5.9716
Max Act: 5.2841. Min Act: -0.1700
Data Index: 7534427 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19