Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3230 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0814. Min Range: -7.0814
Max Act: 7.0814. Min Act: -0.1700
Data Index: 1316643 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0814. Min Range: -7.0814
Max Act: 7.0814. Min Act: -0.1700
Data Index: 4441094 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0814. Min Range: -7.0814
Max Act: 7.0189. Min Act: -0.1700
Data Index: 3785290 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.9564. Min Act: -0.1700
Data Index: 7089947 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.9564. Min Act: -0.1700
Data Index: 5529607 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.9564. Min Act: -0.1700
Data Index: 2746784 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.9564. Min Act: -0.1700
Data Index: 996571 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.9564. Min Act: -0.1700
Data Index: 2015838 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.9564. Min Act: -0.1699
Data Index: 8012850 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.8939. Min Act: -0.1699
Data Index: 787141 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.8939. Min Act: -0.1700
Data Index: 1167837 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.8939. Min Act: -0.1700
Data Index: 7917871 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.8939. Min Act: -0.1700
Data Index: 4344827 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.8939. Min Act: -0.1700
Data Index: 7576891 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.8939. Min Act: -0.1700
Data Index: 134666 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.8939. Min Act: -0.1700
Data Index: 1629516 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.8939. Min Act: -0.1699
Data Index: 152944 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.8314. Min Act: -0.1700
Data Index: 1078210 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.8314. Min Act: -0.1700
Data Index: 404783 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0814. Min Range: -7.0814
Max Act: 6.8314. Min Act: -0.1700
Data Index: 4513264 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19