Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3469 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.6987. Min Act: -0.1700
Data Index: 16096 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.6362. Min Act: -0.1700
Data Index: 5968557 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.6050. Min Act: -0.1700
Data Index: 6513615 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.5737. Min Act: -0.1700
Data Index: 4198173 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4800. Min Act: -0.1700
Data Index: 3454486 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4800. Min Act: -0.1700
Data Index: 5650141 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4487. Min Act: -0.1700
Data Index: 1321629 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4800. Min Act: -0.1700
Data Index: 3910339 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4487. Min Act: -0.1700
Data Index: 6844887 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4175. Min Act: -0.1700
Data Index: 7759084 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4487. Min Act: -0.1700
Data Index: 4542518 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4175. Min Act: -0.1700
Data Index: 7220530 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.3862. Min Act: -0.1700
Data Index: 1916509 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.3550. Min Act: -0.1700
Data Index: 4518971 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.3550. Min Act: -0.1700
Data Index: 2039219 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.3550. Min Act: -0.1700
Data Index: 4687768 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.3550. Min Act: -0.1700
Data Index: 5398388 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.3550. Min Act: -0.1700
Data Index: 7524548 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.3550. Min Act: -0.1700
Data Index: 2625016 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.3550. Min Act: -0.1700
Data Index: 1774910 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19