Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5554 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2774. Min Range: -6.2774
Max Act: 6.2774. Min Act: -0.1700
Data Index: 4562600 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2774. Min Range: -6.2774
Max Act: 6.1212. Min Act: -0.1700
Data Index: 4350586 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2774. Min Range: -6.2774
Max Act: 6.0899. Min Act: -0.1700
Data Index: 4031865 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2774. Min Range: -6.2774
Max Act: 6.0587. Min Act: -0.1700
Data Index: 1452446 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2774. Min Range: -6.2774
Max Act: 6.0587. Min Act: -0.1700
Data Index: 5746967 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.9962. Min Act: -0.1700
Data Index: 3529419 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.9649. Min Act: -0.1700
Data Index: 4977232 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.9337. Min Act: -0.1700
Data Index: 3529417 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.9337. Min Act: -0.1700
Data Index: 7828767 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.9024. Min Act: -0.1700
Data Index: 7828766 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.9024. Min Act: -0.1700
Data Index: 1980059 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.9024. Min Act: -0.1700
Data Index: 7494678 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.8712. Min Act: -0.1700
Data Index: 5921518 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.8712. Min Act: -0.1700
Data Index: 7974302 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.8712. Min Act: -0.1700
Data Index: 8550761 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.8399. Min Act: -0.1700
Data Index: 2448604 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.8399. Min Act: -0.1700
Data Index: 5059574 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.8399. Min Act: -0.1700
Data Index: 5095017 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.8399. Min Act: -0.1700
Data Index: 5241450 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2774. Min Range: -6.2774
Max Act: 5.8399. Min Act: -0.1700
Data Index: 3901483 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19