Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1815 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3686. Min Range: -4.3686
Max Act: 4.3686. Min Act: -0.1700
Data Index: 1223727 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3686. Min Range: -4.3686
Max Act: 4.2123. Min Act: -0.1700
Data Index: 1348178 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3686. Min Range: -4.3686
Max Act: 4.1498. Min Act: -0.1700
Data Index: 5750823 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3686. Min Range: -4.3686
Max Act: 4.1186. Min Act: -0.1700
Data Index: 166501 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3686. Min Range: -4.3686
Max Act: 4.0560. Min Act: -0.1700
Data Index: 6119790 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3686. Min Range: -4.3686
Max Act: 4.0248. Min Act: -0.1700
Data Index: 6565697 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3686. Min Range: -4.3686
Max Act: 3.9935. Min Act: -0.1700
Data Index: 5515868 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3686. Min Range: -4.3686
Max Act: 4.0560. Min Act: -0.1700
Data Index: 2377338 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3686. Min Range: -4.3686
Max Act: 4.0560. Min Act: -0.1700
Data Index: 118214 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3686. Min Range: -4.3686
Max Act: 4.0560. Min Act: -0.1700
Data Index: 3818036 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3686. Min Range: -4.3686
Max Act: 3.9623. Min Act: -0.1700
Data Index: 6621029 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3686. Min Range: -4.3686
Max Act: 3.9623. Min Act: -0.1700
Data Index: 6565696 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3686. Min Range: -4.3686
Max Act: 3.9623. Min Act: -0.1700
Data Index: 2549740 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3686. Min Range: -4.3686
Max Act: 3.9310. Min Act: -0.1700
Data Index: 3269608 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3686. Min Range: -4.3686
Max Act: 3.9623. Min Act: -0.1700
Data Index: 3522604 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3686. Min Range: -4.3686
Max Act: 3.9310. Min Act: -0.1700
Data Index: 4643645 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3686. Min Range: -4.3686
Max Act: 3.9310. Min Act: -0.1700
Data Index: 2514998 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3686. Min Range: -4.3686
Max Act: 3.9310. Min Act: -0.1700
Data Index: 7107198 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3686. Min Range: -4.3686
Max Act: 3.9310. Min Act: -0.1700
Data Index: 4429600 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3686. Min Range: -4.3686
Max Act: 3.8997. Min Act: -0.1700
Data Index: 5642772 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19