Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.2610. Min Act: -0.1700
Data Index: 51874 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.2297. Min Act: -0.1700
Data Index: 3721881 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.1672. Min Act: -0.1700
Data Index: 5502738 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0735. Min Act: -0.1700
Data Index: 985881 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.1047. Min Act: -0.1700
Data Index: 6232208 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.1047. Min Act: -0.1700
Data Index: 6868662 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0422. Min Act: -0.1700
Data Index: 3952630 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0110. Min Act: -0.1700
Data Index: 4998406 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0110. Min Act: -0.1700
Data Index: 3798793 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0110. Min Act: -0.1700
Data Index: 7771348 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9797. Min Act: -0.1700
Data Index: 2586209 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9485. Min Act: -0.1700
Data Index: 530473 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9485. Min Act: -0.1700
Data Index: 3307433 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9485. Min Act: -0.1700
Data Index: 4594859 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9172. Min Act: -0.1700
Data Index: 8496027 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9172. Min Act: -0.1700
Data Index: 1629643 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9485. Min Act: -0.1700
Data Index: 1329435 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.8860. Min Act: -0.1700
Data Index: 4028519 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.8860. Min Act: -0.1700
Data Index: 6916423 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.8547. Min Act: -0.1700
Data Index: 4527234 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19