Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2208 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.2740. Min Act: -0.1700
Data Index: 5032876 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.1490. Min Act: -0.1700
Data Index: 3403928 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.1178. Min Act: -0.1700
Data Index: 154472 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.1178. Min Act: -0.1700
Data Index: 6871046 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.1178. Min Act: -0.1700
Data Index: 2579172 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.1178. Min Act: -0.1700
Data Index: 4005837 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.0553. Min Act: -0.1700
Data Index: 1926465 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.0553. Min Act: -0.1700
Data Index: 1329772 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.0553. Min Act: -0.1700
Data Index: 63291 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2740. Min Range: -5.2740
Max Act: 5.0240. Min Act: -0.1700
Data Index: 8152053 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2740. Min Range: -5.2740
Max Act: 4.9928. Min Act: -0.1700
Data Index: 3502612 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2740. Min Range: -5.2740
Max Act: 4.9615. Min Act: -0.1700
Data Index: 525460 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2740. Min Range: -5.2740
Max Act: 4.9928. Min Act: -0.1700
Data Index: 4982006 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2740. Min Range: -5.2740
Max Act: 4.9928. Min Act: -0.1700
Data Index: 1082183 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2740. Min Range: -5.2740
Max Act: 4.9615. Min Act: -0.1700
Data Index: 4406727 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2740. Min Range: -5.2740
Max Act: 4.9615. Min Act: -0.1700
Data Index: 7368289 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2740. Min Range: -5.2740
Max Act: 4.9615. Min Act: -0.1700
Data Index: 4522711 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2740. Min Range: -5.2740
Max Act: 4.9303. Min Act: -0.1700
Data Index: 2853636 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2740. Min Range: -5.2740
Max Act: 4.9303. Min Act: -0.1700
Data Index: 3816140 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2740. Min Range: -5.2740
Max Act: 4.9615. Min Act: -0.1700
Data Index: 1682614 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19