Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1234 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.2204. Min Act: -0.1700
Data Index: 1035477 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1706. Min Act: -0.1700
Data Index: 6316118 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1706. Min Act: -0.1700
Data Index: 6129580 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1706. Min Act: -0.1698
Data Index: 8093428 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1706. Min Act: -0.1700
Data Index: 6190992 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1373. Min Act: -0.1700
Data Index: 809752 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1206. Min Act: -0.1700
Data Index: 3687708 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1373. Min Act: -0.1700
Data Index: 1579139 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1373. Min Act: -0.1700
Data Index: 3490364 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1373. Min Act: -0.1700
Data Index: 5489081 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1206. Min Act: -0.1700
Data Index: 5795061 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1206. Min Act: -0.1700
Data Index: 2186946 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1206. Min Act: -0.1700
Data Index: 6559938 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1206. Min Act: -0.1700
Data Index: 5879942 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1206. Min Act: -0.1700
Data Index: 7789628 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1373. Min Act: -0.1691
Data Index: 8163304 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1039. Min Act: -0.1700
Data Index: 8212849 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1206. Min Act: -0.1700
Data Index: 8510952 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1039. Min Act: -0.1700
Data Index: 3227363 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2204. Min Range: -2.2204
Max Act: 2.1039. Min Act: -0.1700
Data Index: 1482872 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19