Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5852 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.8173. Min Act: -0.1700
Data Index: 1721170 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.7855. Min Act: -0.1700
Data Index: 6748440 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.8014. Min Act: -0.1700
Data Index: 6457319 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.7695. Min Act: -0.1700
Data Index: 8775347 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.7855. Min Act: -0.1700
Data Index: 1610862 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.7536. Min Act: -0.1700
Data Index: 7804339 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.7536. Min Act: -0.1700
Data Index: 297851 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.7376. Min Act: -0.1700
Data Index: 2068948 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.7216. Min Act: -0.1700
Data Index: 6195994 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.7056. Min Act: -0.1700
Data Index: 3612388 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.7056. Min Act: -0.1700
Data Index: 7444306 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.7056. Min Act: -0.1700
Data Index: 4586561 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.6736. Min Act: -0.1700
Data Index: 7119624 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.6736. Min Act: -0.1700
Data Index: 2677050 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.6415. Min Act: -0.1700
Data Index: 7647305 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.6415. Min Act: -0.1700
Data Index: 3164377 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.6415. Min Act: -0.1700
Data Index: 819596 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.6576. Min Act: -0.1700
Data Index: 268735 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.6255. Min Act: -0.1700
Data Index: 441884 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8173. Min Range: -2.8173
Max Act: 2.6094. Min Act: -0.1700
Data Index: 4936396 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19