Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 58 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.3790. Min Act: -0.1700
Data Index: 2291758 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.3477. Min Act: -0.1700
Data Index: 7711379 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.2692. Min Act: -0.1700
Data Index: 7267407 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.2063. Min Act: -0.1700
Data Index: 7460548 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.2378. Min Act: -0.1700
Data Index: 1292710 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.2221. Min Act: -0.1700
Data Index: 5651075 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.1906. Min Act: -0.1700
Data Index: 3673295 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.1749. Min Act: -0.1700
Data Index: 2762220 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.1434. Min Act: -0.1700
Data Index: 8627209 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.1434. Min Act: -0.1700
Data Index: 8110719 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.1749. Min Act: -0.1700
Data Index: 6999193 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.1434. Min Act: -0.1700
Data Index: 1627187 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.1434. Min Act: -0.1700
Data Index: 6215676 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.1434. Min Act: -0.1700
Data Index: 3426638 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.1434. Min Act: -0.1700
Data Index: 7043082 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.1434. Min Act: -0.1700
Data Index: 1485297 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.1119. Min Act: -0.1700
Data Index: 258879 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.1119. Min Act: -0.1700
Data Index: 53840 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.0961. Min Act: -0.1700
Data Index: 7163988 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3790. Min Range: -3.3790
Max Act: 3.0804. Min Act: -0.1700
Data Index: 6177894 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19