Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4957 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0036. Min Range: -6.0036
Max Act: 6.0036. Min Act: -0.1700
Data Index: 3356900 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.9411. Min Act: -0.1700
Data Index: 3650149 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.9099. Min Act: -0.1700
Data Index: 2592743 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.8474. Min Act: -0.1700
Data Index: 2433245 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.8161. Min Act: -0.1700
Data Index: 6108795 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.8161. Min Act: -0.1700
Data Index: 3770601 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.8161. Min Act: -0.1700
Data Index: 4111797 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.8161. Min Act: -0.1700
Data Index: 5561979 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.8161. Min Act: -0.1700
Data Index: 353888 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.7849. Min Act: -0.1700
Data Index: 1373097 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.7536. Min Act: -0.1700
Data Index: 1110012 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.7536. Min Act: -0.1700
Data Index: 7983327 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.7536. Min Act: -0.1700
Data Index: 8069141 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.7536. Min Act: -0.1700
Data Index: 7757448 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.7224. Min Act: -0.1700
Data Index: 8178087 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.7536. Min Act: -0.1700
Data Index: 1395996 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.7536. Min Act: -0.1700
Data Index: 8540688 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.7536. Min Act: -0.1700
Data Index: 8664718 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.7536. Min Act: -0.1700
Data Index: 6599605 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0036. Min Range: -6.0036
Max Act: 5.7224. Min Act: -0.1700
Data Index: 7713705 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19