Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 41 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1914. Min Act: -0.1355
Data Index: 2498640 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1562. Min Act: -0.1152
Data Index: 7119425 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1562. Min Act: -0.1268
Data Index: 98507 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1386. Min Act: -0.1525
Data Index: 8312004 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1474. Min Act: -0.1411
Data Index: 5324235 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1386. Min Act: -0.1235
Data Index: 3797853 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1299. Min Act: -0.1525
Data Index: 5731563 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1299. Min Act: -0.1652
Data Index: 2589956 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1299. Min Act: -0.1520
Data Index: 5651918 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1211. Min Act: -0.1528
Data Index: 6220757 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1386. Min Act: -0.1605
Data Index: 3609115 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1299. Min Act: -0.1429
Data Index: 7569788 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1211. Min Act: -0.1620
Data Index: 1424735 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1299. Min Act: -0.1448
Data Index: 5081429 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1299. Min Act: -0.1466
Data Index: 2869923 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1211. Min Act: -0.1488
Data Index: 2855495 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1211. Min Act: -0.1605
Data Index: 2785077 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1211. Min Act: -0.1329
Data Index: 1458256 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1211. Min Act: -0.1520
Data Index: 6165598 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1914. Min Range: -1.1914
Max Act: 1.1211. Min Act: -0.1149
Data Index: 346953 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19