Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3950 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.6136. Min Act: -0.1700
Data Index: 8313046 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.4883. Min Act: -0.1700
Data Index: 6774280 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.3316. Min Act: -0.1700
Data Index: 5381169 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.2216. Min Act: -0.1700
Data Index: 1602561 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.1587. Min Act: -0.1700
Data Index: 7262242 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.1745. Min Act: -0.1700
Data Index: 8470916 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.1430. Min Act: -0.1700
Data Index: 8215888 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.1430. Min Act: -0.1700
Data Index: 7044349 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.0957. Min Act: -0.1700
Data Index: 8261569 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.0799. Min Act: -0.1700
Data Index: 3849558 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.0642. Min Act: -0.1700
Data Index: 6697713 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.0957. Min Act: -0.1700
Data Index: 2248459 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.0642. Min Act: -0.1700
Data Index: 205191 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.0642. Min Act: -0.1700
Data Index: 3085461 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.0642. Min Act: -0.1700
Data Index: 6945845 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.0484. Min Act: -0.1700
Data Index: 4990205 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.0642. Min Act: -0.1700
Data Index: 4235153 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.0326. Min Act: -0.1700
Data Index: 5589276 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.0484. Min Act: -0.1700
Data Index: 3811643 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6136. Min Range: -3.6136
Max Act: 3.0168. Min Act: -0.1700
Data Index: 7782445 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19