Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4602 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.6993. Min Act: -0.1700
Data Index: 3188099 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.6513. Min Act: -0.1700
Data Index: 7956575 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.6673. Min Act: -0.1700
Data Index: 8756881 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.6031. Min Act: -0.1700
Data Index: 5011226 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.6031. Min Act: -0.1700
Data Index: 2700680 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5870. Min Act: -0.1700
Data Index: 5077982 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5708. Min Act: -0.1700
Data Index: 3522789 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5547. Min Act: -0.1700
Data Index: 8756886 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5547. Min Act: -0.1700
Data Index: 3981362 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5386. Min Act: -0.1700
Data Index: 7201065 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5386. Min Act: -0.1700
Data Index: 5625821 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5386. Min Act: -0.1700
Data Index: 1731842 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5386. Min Act: -0.1700
Data Index: 3262819 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5062. Min Act: -0.1700
Data Index: 2700679 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5062. Min Act: -0.1700
Data Index: 4609259 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5062. Min Act: -0.1700
Data Index: 6141652 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5062. Min Act: -0.1700
Data Index: 3471927 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.4900. Min Act: -0.1700
Data Index: 7760481 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5062. Min Act: -0.1700
Data Index: 8733464 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5062. Min Act: -0.1700
Data Index: 3675246 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19