Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2567 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0034. Min Range: -5.0034
Max Act: 5.0034. Min Act: -0.1700
Data Index: 5057658 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.8471. Min Act: -0.1700
Data Index: 8594914 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.8159. Min Act: -0.1700
Data Index: 8296175 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.7846. Min Act: -0.1700
Data Index: 291413 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.7534. Min Act: -0.1700
Data Index: 4449901 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.7534. Min Act: -0.1700
Data Index: 291398 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.7221. Min Act: -0.1700
Data Index: 7744067 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.6909. Min Act: -0.1700
Data Index: 6036927 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.6909. Min Act: -0.1700
Data Index: 8538728 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.6596. Min Act: -0.1700
Data Index: 2903656 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.6596. Min Act: -0.1700
Data Index: 2010728 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.6596. Min Act: -0.1700
Data Index: 7406418 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.6596. Min Act: -0.1700
Data Index: 3006848 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.6284. Min Act: -0.1700
Data Index: 2193361 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.6284. Min Act: -0.1700
Data Index: 6087468 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.6284. Min Act: -0.1700
Data Index: 2355365 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.5971. Min Act: -0.1700
Data Index: 7047047 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.5971. Min Act: -0.1700
Data Index: 6685183 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.5971. Min Act: -0.1700
Data Index: 2257091 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0034. Min Range: -5.0034
Max Act: 4.5659. Min Act: -0.1700
Data Index: 6414755 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19