Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 698 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.2373. Min Act: -0.1700
Data Index: 2912806 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.2197. Min Act: -0.1700
Data Index: 7594055 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.2373. Min Act: -0.1700
Data Index: 1170684 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.2197. Min Act: -0.1700
Data Index: 5284131 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.2197. Min Act: -0.1700
Data Index: 4001187 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.2021. Min Act: -0.1700
Data Index: 1513549 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.2021. Min Act: -0.1700
Data Index: 4456715 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.2021. Min Act: -0.1700
Data Index: 4456718 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.2021. Min Act: -0.1700
Data Index: 5265953 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.1845. Min Act: -0.1700
Data Index: 5161072 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.1845. Min Act: -0.1700
Data Index: 4149987 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.1845. Min Act: -0.1700
Data Index: 2181310 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.1669. Min Act: -0.1700
Data Index: 8716419 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.1845. Min Act: -0.1700
Data Index: 7644614 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.1845. Min Act: -0.1700
Data Index: 1858850 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.1669. Min Act: -0.1700
Data Index: 3992887 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.1669. Min Act: -0.1700
Data Index: 1462273 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.1493. Min Act: -0.1700
Data Index: 570157 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.1493. Min Act: -0.1700
Data Index: 1672737 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2373. Min Range: -1.2373
Max Act: 1.1493. Min Act: -0.1700
Data Index: 3988193 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19