Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3416 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.8554. Min Act: -0.1700
Data Index: 4572107 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.8241. Min Act: -0.1700
Data Index: 1164222 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.8241. Min Act: -0.1700
Data Index: 2731302 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.7615. Min Act: -0.1700
Data Index: 4434114 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.7615. Min Act: -0.1700
Data Index: 2035519 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.6990. Min Act: -0.1700
Data Index: 4417480 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.6677. Min Act: -0.1700
Data Index: 8638817 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.6364. Min Act: -0.1700
Data Index: 5612793 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.6364. Min Act: -0.1700
Data Index: 1870776 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.6677. Min Act: -0.1700
Data Index: 7749532 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.6364. Min Act: -0.1700
Data Index: 8431703 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.6207. Min Act: -0.1700
Data Index: 4356087 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.6207. Min Act: -0.1700
Data Index: 4410045 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.6207. Min Act: -0.1700
Data Index: 7969935 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.5894. Min Act: -0.1700
Data Index: 2112961 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.6051. Min Act: -0.1700
Data Index: 5984253 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.6207. Min Act: -0.1700
Data Index: 13975 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.6207. Min Act: -0.1700
Data Index: 986745 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.5894. Min Act: -0.1700
Data Index: 5113175 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8554. Min Range: -3.8554
Max Act: 3.6051. Min Act: -0.1700
Data Index: 6120672 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19