Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1041 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1964. Min Range: -4.1964
Max Act: 4.1964. Min Act: -0.1700
Data Index: 7201399 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1964. Min Range: -4.1964
Max Act: 4.1339. Min Act: -0.1700
Data Index: 302730 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1964. Min Range: -4.1964
Max Act: 4.0402. Min Act: -0.1700
Data Index: 5045127 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1964. Min Range: -4.1964
Max Act: 3.9464. Min Act: -0.1700
Data Index: 3059830 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1964. Min Range: -4.1964
Max Act: 3.9776. Min Act: -0.1700
Data Index: 4003216 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1964. Min Range: -4.1964
Max Act: 3.9464. Min Act: -0.1700
Data Index: 5616673 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1964. Min Range: -4.1964
Max Act: 3.9464. Min Act: -0.1700
Data Index: 5032146 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1964. Min Range: -4.1964
Max Act: 3.9464. Min Act: -0.1700
Data Index: 4713026 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1964. Min Range: -4.1964
Max Act: 3.9151. Min Act: -0.1700
Data Index: 1616118 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1964. Min Range: -4.1964
Max Act: 3.9151. Min Act: -0.1700
Data Index: 2284786 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1964. Min Range: -4.1964
Max Act: 3.8839. Min Act: -0.1700
Data Index: 2553238 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1964. Min Range: -4.1964
Max Act: 3.8682. Min Act: -0.1700
Data Index: 4750601 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1964. Min Range: -4.1964
Max Act: 3.8839. Min Act: -0.1700
Data Index: 4380431 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1964. Min Range: -4.1964
Max Act: 3.8526. Min Act: -0.1700
Data Index: 7058162 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1964. Min Range: -4.1964
Max Act: 3.8526. Min Act: -0.1700
Data Index: 2375578 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1964. Min Range: -4.1964
Max Act: 3.8526. Min Act: -0.1700
Data Index: 7653764 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1964. Min Range: -4.1964
Max Act: 3.8526. Min Act: -0.1700
Data Index: 27045 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1964. Min Range: -4.1964
Max Act: 3.8370. Min Act: -0.1700
Data Index: 7024027 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1964. Min Range: -4.1964
Max Act: 3.8213. Min Act: -0.1700
Data Index: 1226294 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1964. Min Range: -4.1964
Max Act: 3.8526. Min Act: -0.1700
Data Index: 5077639 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19