Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1480 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5032. Min Range: -6.5032
Max Act: 6.5032. Min Act: -0.1700
Data Index: 2045450 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5032. Min Range: -6.5032
Max Act: 6.2845. Min Act: -0.1700
Data Index: 3115056 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5032. Min Range: -6.5032
Max Act: 6.2845. Min Act: -0.1700
Data Index: 3080751 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5032. Min Range: -6.5032
Max Act: 6.3157. Min Act: -0.1700
Data Index: 7249117 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5032. Min Range: -6.5032
Max Act: 6.1907. Min Act: -0.1700
Data Index: 8136655 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5032. Min Range: -6.5032
Max Act: 6.1907. Min Act: -0.1700
Data Index: 391671 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5032. Min Range: -6.5032
Max Act: 6.1282. Min Act: -0.1700
Data Index: 3593501 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5032. Min Range: -6.5032
Max Act: 6.0970. Min Act: -0.1700
Data Index: 7590182 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5032. Min Range: -6.5032
Max Act: 6.0345. Min Act: -0.1700
Data Index: 7171811 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5032. Min Range: -6.5032
Max Act: 6.0970. Min Act: -0.1700
Data Index: 7333620 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5032. Min Range: -6.5032
Max Act: 6.0657. Min Act: -0.1700
Data Index: 1435457 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5032. Min Range: -6.5032
Max Act: 6.0345. Min Act: -0.1700
Data Index: 3676912 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5032. Min Range: -6.5032
Max Act: 6.0032. Min Act: -0.1700
Data Index: 5897173 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5032. Min Range: -6.5032
Max Act: 6.0032. Min Act: -0.1700
Data Index: 4981141 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5032. Min Range: -6.5032
Max Act: 5.9720. Min Act: -0.1700
Data Index: 2717863 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5032. Min Range: -6.5032
Max Act: 5.9407. Min Act: -0.1700
Data Index: 6964175 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5032. Min Range: -6.5032
Max Act: 5.9407. Min Act: -0.1700
Data Index: 6820471 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5032. Min Range: -6.5032
Max Act: 5.9095. Min Act: -0.1700
Data Index: 530174 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5032. Min Range: -6.5032
Max Act: 5.9095. Min Act: -0.1700
Data Index: 2973614 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5032. Min Range: -6.5032
Max Act: 5.9095. Min Act: -0.1700
Data Index: 5850565 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19