Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2296 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2896. Min Range: -6.2896
Max Act: 6.2896. Min Act: -0.1700
Data Index: 6429387 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2896. Min Range: -6.2896
Max Act: 6.1646. Min Act: -0.1700
Data Index: 1492886 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2896. Min Range: -6.2896
Max Act: 6.1333. Min Act: -0.1700
Data Index: 8692193 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2896. Min Range: -6.2896
Max Act: 6.1333. Min Act: -0.1700
Data Index: 5381418 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2896. Min Range: -6.2896
Max Act: 6.1333. Min Act: -0.1700
Data Index: 1460828 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2896. Min Range: -6.2896
Max Act: 6.0708. Min Act: -0.1700
Data Index: 1636714 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2896. Min Range: -6.2896
Max Act: 6.0708. Min Act: -0.1700
Data Index: 6356114 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2896. Min Range: -6.2896
Max Act: 6.0083. Min Act: -0.1700
Data Index: 8319216 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2896. Min Range: -6.2896
Max Act: 6.0396. Min Act: -0.1700
Data Index: 2100743 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2896. Min Range: -6.2896
Max Act: 6.0396. Min Act: -0.1700
Data Index: 6269890 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2896. Min Range: -6.2896
Max Act: 6.0083. Min Act: -0.1700
Data Index: 2693826 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2896. Min Range: -6.2896
Max Act: 5.9771. Min Act: -0.1700
Data Index: 8246975 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2896. Min Range: -6.2896
Max Act: 5.9771. Min Act: -0.1700
Data Index: 7772719 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2896. Min Range: -6.2896
Max Act: 5.9771. Min Act: -0.1700
Data Index: 1886732 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2896. Min Range: -6.2896
Max Act: 5.9771. Min Act: -0.1700
Data Index: 8808710 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2896. Min Range: -6.2896
Max Act: 5.9771. Min Act: -0.1700
Data Index: 8618744 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2896. Min Range: -6.2896
Max Act: 5.9146. Min Act: -0.1700
Data Index: 1814012 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2896. Min Range: -6.2896
Max Act: 5.9458. Min Act: -0.1700
Data Index: 3223613 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2896. Min Range: -6.2896
Max Act: 5.9458. Min Act: -0.1700
Data Index: 7424516 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2896. Min Range: -6.2896
Max Act: 5.9458. Min Act: -0.1700
Data Index: 4765235 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19