Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4138 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.2610. Min Act: -0.1700
Data Index: 2906651 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.1985. Min Act: -0.1700
Data Index: 1561271 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0422. Min Act: -0.1700
Data Index: 7078754 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9797. Min Act: -0.1700
Data Index: 3489849 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9797. Min Act: -0.1700
Data Index: 2080681 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.8860. Min Act: -0.1700
Data Index: 1704133 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.8860. Min Act: -0.1700
Data Index: 6205409 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.8860. Min Act: -0.1700
Data Index: 7853662 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.8547. Min Act: -0.1700
Data Index: 7964585 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.8547. Min Act: -0.1700
Data Index: 5568454 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.7922. Min Act: -0.1700
Data Index: 2539818 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.8235. Min Act: -0.1700
Data Index: 4864118 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.8235. Min Act: -0.1700
Data Index: 8244464 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.8235. Min Act: -0.1700
Data Index: 8771895 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.8547. Min Act: -0.1700
Data Index: 4827256 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.7922. Min Act: -0.1700
Data Index: 8002217 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.7922. Min Act: -0.1700
Data Index: 2292087 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.7922. Min Act: -0.1700
Data Index: 5523477 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.7610. Min Act: -0.1700
Data Index: 2488746 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.7610. Min Act: -0.1700
Data Index: 1394989 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19