Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2774 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.8000. Min Act: -0.1700
Data Index: 1961748 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7827. Min Act: -0.1695
Data Index: 1654475 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7827. Min Act: -0.1700
Data Index: 1543925 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7827. Min Act: -0.1700
Data Index: 5092159 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7655. Min Act: -0.1700
Data Index: 7853723 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7741. Min Act: -0.1695
Data Index: 6380245 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7569. Min Act: -0.1700
Data Index: 4686064 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7569. Min Act: -0.1700
Data Index: 2137287 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7569. Min Act: -0.1700
Data Index: 4425790 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7482. Min Act: -0.1700
Data Index: 1058478 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7482. Min Act: -0.1700
Data Index: 6694184 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7309. Min Act: -0.1700
Data Index: 2674940 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7396. Min Act: -0.1700
Data Index: 7763562 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7223. Min Act: -0.1700
Data Index: 8336611 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7223. Min Act: -0.1700
Data Index: 8581091 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7223. Min Act: -0.1700
Data Index: 6150251 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7223. Min Act: -0.1700
Data Index: 553212 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7223. Min Act: -0.1700
Data Index: 8758675 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7136. Min Act: -0.1700
Data Index: 2423060 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8000. Min Range: -1.8000
Max Act: 1.7136. Min Act: -0.1700
Data Index: 1534153 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19