Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4059 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0843. Min Range: -5.0843
Max Act: 5.0843. Min Act: -0.1700
Data Index: 1634075 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.9593. Min Act: -0.1700
Data Index: 5123806 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.9280. Min Act: -0.1700
Data Index: 5123800 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.9905. Min Act: -0.1700
Data Index: 2230548 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.9593. Min Act: -0.1700
Data Index: 5003675 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.9280. Min Act: -0.1700
Data Index: 7076829 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.8655. Min Act: -0.1700
Data Index: 8311781 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.7718. Min Act: -0.1700
Data Index: 6458969 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.8030. Min Act: -0.1700
Data Index: 8017723 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.7405. Min Act: -0.1700
Data Index: 7691747 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.7405. Min Act: -0.1700
Data Index: 2156760 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.7718. Min Act: -0.1700
Data Index: 3553270 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.7718. Min Act: -0.1700
Data Index: 3492220 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.7405. Min Act: -0.1700
Data Index: 2882507 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.7718. Min Act: -0.1700
Data Index: 1279264 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.7405. Min Act: -0.1700
Data Index: 2759287 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.7405. Min Act: -0.1700
Data Index: 5420800 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.7093. Min Act: -0.1700
Data Index: 19893 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.7405. Min Act: -0.1700
Data Index: 6145311 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0843. Min Range: -5.0843
Max Act: 4.7405. Min Act: -0.1700
Data Index: 2882509 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19