Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1935 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2304. Min Range: -6.2304
Max Act: 6.2304. Min Act: -0.1700
Data Index: 8270903 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2304. Min Range: -6.2304
Max Act: 6.1991. Min Act: -0.1700
Data Index: 5503721 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2304. Min Range: -6.2304
Max Act: 6.1991. Min Act: -0.1700
Data Index: 8270904 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2304. Min Range: -6.2304
Max Act: 6.0741. Min Act: -0.1700
Data Index: 8270890 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2304. Min Range: -6.2304
Max Act: 6.0741. Min Act: -0.1700
Data Index: 8270887 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2304. Min Range: -6.2304
Max Act: 6.0429. Min Act: -0.1700
Data Index: 5503717 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2304. Min Range: -6.2304
Max Act: 6.0741. Min Act: -0.1700
Data Index: 4939055 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2304. Min Range: -6.2304
Max Act: 6.0116. Min Act: -0.1699
Data Index: 4939029 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2304. Min Range: -6.2304
Max Act: 6.0116. Min Act: -0.1700
Data Index: 8270889 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2304. Min Range: -6.2304
Max Act: 6.0429. Min Act: -0.1696
Data Index: 4939040 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2304. Min Range: -6.2304
Max Act: 6.0116. Min Act: -0.1700
Data Index: 8270892 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2304. Min Range: -6.2304
Max Act: 6.0429. Min Act: -0.1700
Data Index: 8270906 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2304. Min Range: -6.2304
Max Act: 5.9491. Min Act: -0.1697
Data Index: 4939048 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2304. Min Range: -6.2304
Max Act: 6.0116. Min Act: -0.1699
Data Index: 4939049 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2304. Min Range: -6.2304
Max Act: 5.9491. Min Act: -0.1700
Data Index: 4939041 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2304. Min Range: -6.2304
Max Act: 5.9179. Min Act: -0.1700
Data Index: 5503720 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2304. Min Range: -6.2304
Max Act: 5.9491. Min Act: -0.1700
Data Index: 8270898 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2304. Min Range: -6.2304
Max Act: 5.9491. Min Act: -0.1700
Data Index: 4939046 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2304. Min Range: -6.2304
Max Act: 5.9179. Min Act: -0.1700
Data Index: 4939050 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2304. Min Range: -6.2304
Max Act: 5.8866. Min Act: -0.1700
Data Index: 4939037 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19