Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1603 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3671. Min Range: -7.3671
Max Act: 7.3671. Min Act: -0.1700
Data Index: 528133 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.9921. Min Act: -0.1700
Data Index: 983203 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.9609. Min Act: -0.1700
Data Index: 6373290 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.8671. Min Act: -0.1700
Data Index: 1438412 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.8671. Min Act: -0.1700
Data Index: 3595576 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.8359. Min Act: -0.1700
Data Index: 6980045 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.8046. Min Act: -0.1700
Data Index: 2520231 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.7734. Min Act: -0.1700
Data Index: 7953644 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.7734. Min Act: -0.1700
Data Index: 3244604 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.7421. Min Act: -0.1700
Data Index: 5388012 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.7109. Min Act: -0.1700
Data Index: 5867342 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.7109. Min Act: -0.1700
Data Index: 8407873 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.6796. Min Act: -0.1700
Data Index: 1566343 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.6796. Min Act: -0.1700
Data Index: 5888731 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.6796. Min Act: -0.1700
Data Index: 8378087 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.6796. Min Act: -0.1700
Data Index: 7553942 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.6484. Min Act: -0.1700
Data Index: 7532711 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.6796. Min Act: -0.1700
Data Index: 2502749 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.6171. Min Act: -0.1700
Data Index: 1301678 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3671. Min Range: -7.3671
Max Act: 6.6484. Min Act: -0.1700
Data Index: 3120095 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19