Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4754 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.5815. Min Act: -0.1700
Data Index: 2876878 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.3628. Min Act: -0.1700
Data Index: 305187 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.3628. Min Act: -0.1700
Data Index: 8068138 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.3628. Min Act: -0.1700
Data Index: 8400002 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.3315. Min Act: -0.1700
Data Index: 6195796 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.3003. Min Act: -0.1700
Data Index: 1305526 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.2690. Min Act: -0.1700
Data Index: 6141140 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.3003. Min Act: -0.1700
Data Index: 5280563 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.2690. Min Act: -0.1700
Data Index: 218498 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.2690. Min Act: -0.1700
Data Index: 3575792 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.2690. Min Act: -0.1700
Data Index: 4127663 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.2065. Min Act: -0.1700
Data Index: 5819707 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.2378. Min Act: -0.1700
Data Index: 3529094 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.2378. Min Act: -0.1700
Data Index: 6445492 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.2065. Min Act: -0.1700
Data Index: 668114 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.2065. Min Act: -0.1700
Data Index: 2883644 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.2065. Min Act: -0.1700
Data Index: 2869489 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.1753. Min Act: -0.1700
Data Index: 695526 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.1440. Min Act: -0.1699
Data Index: 4608499 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5815. Min Range: -6.5815
Max Act: 6.0815. Min Act: -0.1700
Data Index: 4378817 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19