Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3881 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2284. Min Range: -9.2284
Max Act: 9.2284. Min Act: -0.1700
Data Index: 7070700 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2284. Min Range: -9.2284
Max Act: 9.0409. Min Act: -0.1700
Data Index: 2599268 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.8534. Min Act: -0.1700
Data Index: 3978623 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.6659. Min Act: -0.1700
Data Index: 4206272 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.6659. Min Act: -0.1700
Data Index: 4896896 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.6034. Min Act: -0.1700
Data Index: 6752170 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.6034. Min Act: -0.1700
Data Index: 1522640 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.6659. Min Act: -0.1700
Data Index: 3827886 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.6034. Min Act: -0.1700
Data Index: 6544171 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.4784. Min Act: -0.1700
Data Index: 6063995 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.4159. Min Act: -0.1700
Data Index: 3611090 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.4784. Min Act: -0.1700
Data Index: 7329967 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.4159. Min Act: -0.1700
Data Index: 6774394 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.4159. Min Act: -0.1700
Data Index: 6179242 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.4159. Min Act: -0.1700
Data Index: 6774399 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.3534. Min Act: -0.1700
Data Index: 8556263 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.3534. Min Act: -0.1700
Data Index: 6913831 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.3534. Min Act: -0.1700
Data Index: 1100799 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.2909. Min Act: -0.1700
Data Index: 2502709 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2284. Min Range: -9.2284
Max Act: 8.2909. Min Act: -0.1700
Data Index: 2122803 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19