Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 981 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.7035. Min Act: -0.1700
Data Index: 5903234 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.6410. Min Act: -0.1700
Data Index: 6109655 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.3598. Min Act: -0.1700
Data Index: 8634001 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.3285. Min Act: -0.1700
Data Index: 1632063 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.3598. Min Act: -0.1700
Data Index: 3577353 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.2973. Min Act: -0.1700
Data Index: 3505204 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.2973. Min Act: -0.1700
Data Index: 7736317 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.2973. Min Act: -0.1700
Data Index: 7764295 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.2973. Min Act: -0.1700
Data Index: 2340921 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.2035. Min Act: -0.1700
Data Index: 8540201 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.2348. Min Act: -0.1700
Data Index: 6064181 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.2035. Min Act: -0.1700
Data Index: 2924705 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.2035. Min Act: -0.1700
Data Index: 769933 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.2348. Min Act: -0.1700
Data Index: 8171116 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.2660. Min Act: -0.1700
Data Index: 8778838 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.1723. Min Act: -0.1700
Data Index: 3158114 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.1723. Min Act: -0.1700
Data Index: 3071929 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.1723. Min Act: -0.1700
Data Index: 8305080 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.2035. Min Act: -0.1700
Data Index: 8731891 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7035. Min Range: -5.7035
Max Act: 5.1410. Min Act: -0.1700
Data Index: 1527480 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19