Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2272 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.1945. Min Act: -0.1700
Data Index: 1590468 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.1279. Min Act: -0.1700
Data Index: 6656087 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.1279. Min Act: -0.1700
Data Index: 4919687 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.1112. Min Act: -0.1700
Data Index: 3760260 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.1112. Min Act: -0.1699
Data Index: 743348 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.0944. Min Act: -0.1700
Data Index: 1013811 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.0944. Min Act: -0.1700
Data Index: 2097690 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.0944. Min Act: -0.1700
Data Index: 2540330 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.0944. Min Act: -0.1700
Data Index: 3837204 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.0777. Min Act: -0.1700
Data Index: 5848818 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.0777. Min Act: -0.1700
Data Index: 2225027 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.0777. Min Act: -0.1700
Data Index: 5839784 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.0777. Min Act: -0.1700
Data Index: 4115884 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.0609. Min Act: -0.1700
Data Index: 285395 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.0609. Min Act: -0.1700
Data Index: 2804786 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.0609. Min Act: -0.1700
Data Index: 1010790 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.0777. Min Act: -0.1700
Data Index: 2976341 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.0609. Min Act: -0.1700
Data Index: 3374740 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.0609. Min Act: -0.1700
Data Index: 4067022 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1945. Min Range: -2.1945
Max Act: 2.0609. Min Act: -0.1700
Data Index: 366129 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19