Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5878 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1267. Min Range: -9.1267
Max Act: 9.1267. Min Act: -0.1700
Data Index: 2631065 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1267. Min Range: -9.1267
Max Act: 8.6892. Min Act: -0.1700
Data Index: 8546047 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1267. Min Range: -9.1267
Max Act: 8.4392. Min Act: -0.1700
Data Index: 824385 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1267. Min Range: -9.1267
Max Act: 8.3767. Min Act: -0.1700
Data Index: 5218729 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1267. Min Range: -9.1267
Max Act: 8.3142. Min Act: -0.1700
Data Index: 5949313 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1267. Min Range: -9.1267
Max Act: 8.3142. Min Act: -0.1700
Data Index: 7683996 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1267. Min Range: -9.1267
Max Act: 8.2517. Min Act: -0.1700
Data Index: 2615009 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1267. Min Range: -9.1267
Max Act: 8.2517. Min Act: -0.1700
Data Index: 4884184 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1267. Min Range: -9.1267
Max Act: 8.1892. Min Act: -0.1700
Data Index: 6109449 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1267. Min Range: -9.1267
Max Act: 8.1267. Min Act: -0.1700
Data Index: 8233803 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1267. Min Range: -9.1267
Max Act: 8.1267. Min Act: -0.1700
Data Index: 3336116 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1267. Min Range: -9.1267
Max Act: 8.1267. Min Act: -0.1700
Data Index: 8362248 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1267. Min Range: -9.1267
Max Act: 8.1267. Min Act: -0.1700
Data Index: 7644397 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1267. Min Range: -9.1267
Max Act: 8.1267. Min Act: -0.1700
Data Index: 1557963 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1267. Min Range: -9.1267
Max Act: 8.0642. Min Act: -0.1700
Data Index: 3790442 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1267. Min Range: -9.1267
Max Act: 7.9392. Min Act: -0.1700
Data Index: 2534415 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1267. Min Range: -9.1267
Max Act: 8.0017. Min Act: -0.1700
Data Index: 3790321 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1267. Min Range: -9.1267
Max Act: 7.9392. Min Act: -0.1700
Data Index: 4517190 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1267. Min Range: -9.1267
Max Act: 7.8767. Min Act: -0.1700
Data Index: 6328565 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1267. Min Range: -9.1267
Max Act: 7.9392. Min Act: -0.1700
Data Index: 4517191 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19