Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.5208. Min Act: -0.1700
Data Index: 6082918 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.4271. Min Act: -0.1700
Data Index: 7520100 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.3646. Min Act: -0.1700
Data Index: 4082193 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.3333. Min Act: -0.1700
Data Index: 1719275 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.3021. Min Act: -0.1700
Data Index: 1719273 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.2708. Min Act: -0.1700
Data Index: 2296108 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.2396. Min Act: -0.1700
Data Index: 5910601 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.2083. Min Act: -0.1700
Data Index: 1666664 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.1458. Min Act: -0.1700
Data Index: 6772407 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.1458. Min Act: -0.1700
Data Index: 3714388 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.0833. Min Act: -0.1700
Data Index: 5198182 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.0521. Min Act: -0.1700
Data Index: 1666666 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.0833. Min Act: -0.1700
Data Index: 4169894 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.0833. Min Act: -0.1700
Data Index: 5056524 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.0833. Min Act: -0.1700
Data Index: 1666665 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.0833. Min Act: -0.1700
Data Index: 4886291 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.0833. Min Act: -0.1700
Data Index: 6451183 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.1146. Min Act: -0.1700
Data Index: 4374623 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.0833. Min Act: -0.1700
Data Index: 781509 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5208. Min Range: -6.5208
Max Act: 6.0833. Min Act: -0.1700
Data Index: 327865 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19