Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 783 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2256. Min Range: -5.2256
Max Act: 5.2256. Min Act: -0.1700
Data Index: 2876271 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2256. Min Range: -5.2256
Max Act: 5.1943. Min Act: -0.1700
Data Index: 4211797 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2256. Min Range: -5.2256
Max Act: 5.1943. Min Act: -0.1700
Data Index: 6031462 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2256. Min Range: -5.2256
Max Act: 5.1943. Min Act: -0.1700
Data Index: 6109380 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2256. Min Range: -5.2256
Max Act: 5.1631. Min Act: -0.1700
Data Index: 7271172 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2256. Min Range: -5.2256
Max Act: 5.1318. Min Act: -0.1700
Data Index: 8684381 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2256. Min Range: -5.2256
Max Act: 5.0693. Min Act: -0.1700
Data Index: 5172737 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2256. Min Range: -5.2256
Max Act: 5.0381. Min Act: -0.1700
Data Index: 5144625 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2256. Min Range: -5.2256
Max Act: 5.0381. Min Act: -0.1700
Data Index: 2577317 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2256. Min Range: -5.2256
Max Act: 5.0068. Min Act: -0.1700
Data Index: 217782 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2256. Min Range: -5.2256
Max Act: 4.9756. Min Act: -0.1700
Data Index: 7388 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2256. Min Range: -5.2256
Max Act: 5.0381. Min Act: -0.1700
Data Index: 20535 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2256. Min Range: -5.2256
Max Act: 5.0068. Min Act: -0.1700
Data Index: 2390296 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2256. Min Range: -5.2256
Max Act: 5.0068. Min Act: -0.1700
Data Index: 8418560 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2256. Min Range: -5.2256
Max Act: 5.0068. Min Act: -0.1700
Data Index: 2876282 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2256. Min Range: -5.2256
Max Act: 4.9756. Min Act: -0.1700
Data Index: 7121687 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2256. Min Range: -5.2256
Max Act: 4.9443. Min Act: -0.1700
Data Index: 7178988 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2256. Min Range: -5.2256
Max Act: 5.0068. Min Act: -0.1700
Data Index: 1782675 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2256. Min Range: -5.2256
Max Act: 5.0068. Min Act: -0.1700
Data Index: 8510013 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2256. Min Range: -5.2256
Max Act: 4.9443. Min Act: -0.1700
Data Index: 1946668 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19