Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 858 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0735. Min Range: -6.0735
Max Act: 6.0735. Min Act: -0.1700
Data Index: 3184792 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.9797. Min Act: -0.1700
Data Index: 3536030 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.9485. Min Act: -0.1700
Data Index: 6134697 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.9172. Min Act: -0.1700
Data Index: 3038304 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.9172. Min Act: -0.1700
Data Index: 1346374 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.9172. Min Act: -0.1700
Data Index: 3683863 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.8235. Min Act: -0.1700
Data Index: 8722311 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.8235. Min Act: -0.1700
Data Index: 129823 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.8235. Min Act: -0.1700
Data Index: 3835470 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.8235. Min Act: -0.1700
Data Index: 7925309 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.8235. Min Act: -0.1700
Data Index: 4899482 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.7922. Min Act: -0.1700
Data Index: 3753296 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.7922. Min Act: -0.1700
Data Index: 5614108 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.7922. Min Act: -0.1700
Data Index: 8642026 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.7922. Min Act: -0.1700
Data Index: 6063930 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.7922. Min Act: -0.1700
Data Index: 8042538 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.7610. Min Act: -0.1700
Data Index: 6763117 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.7610. Min Act: -0.1700
Data Index: 1510782 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.7610. Min Act: -0.1700
Data Index: 1917664 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0735. Min Range: -6.0735
Max Act: 5.7610. Min Act: -0.1700
Data Index: 166264 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19