Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3970 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.8512. Min Act: -0.1700
Data Index: 2110637 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.7417. Min Act: -0.1700
Data Index: 644832 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.7104. Min Act: -0.1700
Data Index: 8534737 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.6009. Min Act: -0.1700
Data Index: 1064830 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.5853. Min Act: -0.1700
Data Index: 2221569 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.5383. Min Act: -0.1700
Data Index: 7788104 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.5540. Min Act: -0.1700
Data Index: 6199729 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.5383. Min Act: -0.1700
Data Index: 1047957 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.5070. Min Act: -0.1700
Data Index: 7546259 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.5226. Min Act: -0.1700
Data Index: 2578183 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.5226. Min Act: -0.1700
Data Index: 3437883 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.5070. Min Act: -0.1700
Data Index: 5492116 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.4756. Min Act: -0.1700
Data Index: 4344705 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.4913. Min Act: -0.1700
Data Index: 6692191 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.4913. Min Act: -0.1700
Data Index: 4295792 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.4756. Min Act: -0.1700
Data Index: 3004992 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.4756. Min Act: -0.1700
Data Index: 793909 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.4756. Min Act: -0.1700
Data Index: 2857787 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.4600. Min Act: -0.1700
Data Index: 3823140 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8512. Min Range: -3.8512
Max Act: 3.4756. Min Act: -0.1700
Data Index: 3066114 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19