Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4732 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.2424. Min Act: -0.1700
Data Index: 8312238 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.2424. Min Act: -0.1700
Data Index: 3549075 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.2110. Min Act: -0.1700
Data Index: 2764267 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.2110. Min Act: -0.1700
Data Index: 1283624 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.1795. Min Act: -0.1700
Data Index: 7939238 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.2110. Min Act: -0.1700
Data Index: 7679046 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.2110. Min Act: -0.1700
Data Index: 6964234 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.2110. Min Act: -0.1700
Data Index: 2107165 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.2110. Min Act: -0.1700
Data Index: 1627639 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.2110. Min Act: -0.1700
Data Index: 5601877 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.2110. Min Act: -0.1700
Data Index: 5042459 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.1795. Min Act: -0.1700
Data Index: 4467011 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.2110. Min Act: -0.1700
Data Index: 3849886 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.2110. Min Act: -0.1700
Data Index: 571910 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.2110. Min Act: -0.1700
Data Index: 3540748 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.2110. Min Act: -0.1700
Data Index: 3498287 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.2110. Min Act: -0.1700
Data Index: 1939695 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.1795. Min Act: -0.1700
Data Index: 1415059 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.1795. Min Act: -0.1700
Data Index: 1576329 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2424. Min Range: -3.2424
Max Act: 3.1795. Min Act: -0.1700
Data Index: 1633277 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19