Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3432 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.8960. Min Act: -0.1700
Data Index: 772537 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.8335. Min Act: -0.1700
Data Index: 974344 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.8023. Min Act: -0.1700
Data Index: 235085 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.7710. Min Act: -0.1700
Data Index: 97078 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.7085. Min Act: -0.1700
Data Index: 3348853 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.6773. Min Act: -0.1700
Data Index: 7814828 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.6773. Min Act: -0.1700
Data Index: 4129638 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.6773. Min Act: -0.1700
Data Index: 8098646 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.6773. Min Act: -0.1700
Data Index: 4968893 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.6460. Min Act: -0.1700
Data Index: 8052060 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.6460. Min Act: -0.1700
Data Index: 1627123 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.6460. Min Act: -0.1700
Data Index: 1676832 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.6148. Min Act: -0.1700
Data Index: 3377966 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.6148. Min Act: -0.1700
Data Index: 1601675 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.6148. Min Act: -0.1700
Data Index: 5801531 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.5835. Min Act: -0.1700
Data Index: 1601673 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.5523. Min Act: -0.1700
Data Index: 5801524 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.5523. Min Act: -0.1700
Data Index: 2835565 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.5210. Min Act: -0.1700
Data Index: 943495 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8960. Min Range: -5.8960
Max Act: 5.5210. Min Act: -0.1700
Data Index: 7797485 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19