Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3348 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1146. Min Range: -7.1146
Max Act: 7.1146. Min Act: -0.1700
Data Index: 7332807 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1146. Min Range: -7.1146
Max Act: 7.0521. Min Act: -0.1700
Data Index: 951974 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.9271. Min Act: -0.1700
Data Index: 649718 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.8021. Min Act: -0.1700
Data Index: 1772306 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.7708. Min Act: -0.1700
Data Index: 5574712 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.6146. Min Act: -0.1700
Data Index: 4655545 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.5833. Min Act: -0.1700
Data Index: 3444749 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.5833. Min Act: -0.1700
Data Index: 43043 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.5521. Min Act: -0.1700
Data Index: 2254539 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.5833. Min Act: -0.1700
Data Index: 8109337 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.5521. Min Act: -0.1700
Data Index: 3307988 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.5521. Min Act: -0.1700
Data Index: 7619869 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.5208. Min Act: -0.1700
Data Index: 6171649 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.4896. Min Act: -0.1700
Data Index: 4167499 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.5208. Min Act: -0.1700
Data Index: 8740322 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.4896. Min Act: -0.1700
Data Index: 7144681 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.4583. Min Act: -0.1700
Data Index: 4252291 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.4271. Min Act: -0.1700
Data Index: 4441874 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.4271. Min Act: -0.1700
Data Index: 7689413 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1146. Min Range: -7.1146
Max Act: 6.4271. Min Act: -0.1700
Data Index: 3223872 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19