Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 827 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.5153. Min Act: -0.1700
Data Index: 7815803 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.4216. Min Act: -0.1700
Data Index: 8149166 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.4216. Min Act: -0.1700
Data Index: 2551112 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.2028. Min Act: -0.1700
Data Index: 730500 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.2028. Min Act: -0.1700
Data Index: 7104556 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.1403. Min Act: -0.1700
Data Index: 6305549 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.1091. Min Act: -0.1700
Data Index: 506278 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.1091. Min Act: -0.1700
Data Index: 408550 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0778. Min Act: -0.1700
Data Index: 8222238 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0778. Min Act: -0.1700
Data Index: 1076371 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0778. Min Act: -0.1700
Data Index: 8671319 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0466. Min Act: -0.1700
Data Index: 128791 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0466. Min Act: -0.1700
Data Index: 2353695 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0466. Min Act: -0.1700
Data Index: 2263227 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0466. Min Act: -0.1700
Data Index: 1419152 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0466. Min Act: -0.1700
Data Index: 3691693 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0778. Min Act: -0.1700
Data Index: 4777415 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0153. Min Act: -0.1700
Data Index: 8522781 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0153. Min Act: -0.1700
Data Index: 5204755 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0153. Min Act: -0.1700
Data Index: 7991487 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19