Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2764 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5750. Min Range: -7.5750
Max Act: 7.5750. Min Act: -0.1700
Data Index: 7203929 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5750. Min Range: -7.5750
Max Act: 7.1375. Min Act: -0.1700
Data Index: 6206842 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5750. Min Range: -7.5750
Max Act: 7.0750. Min Act: -0.1700
Data Index: 5668458 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5750. Min Range: -7.5750
Max Act: 7.0750. Min Act: -0.1700
Data Index: 7356025 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5750. Min Range: -7.5750
Max Act: 7.0125. Min Act: -0.1700
Data Index: 1250195 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5750. Min Range: -7.5750
Max Act: 7.0125. Min Act: -0.1700
Data Index: 1023178 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5750. Min Range: -7.5750
Max Act: 7.0125. Min Act: -0.1700
Data Index: 5254147 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5750. Min Range: -7.5750
Max Act: 6.9813. Min Act: -0.1700
Data Index: 6206843 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5750. Min Range: -7.5750
Max Act: 6.9813. Min Act: -0.1700
Data Index: 5950574 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5750. Min Range: -7.5750
Max Act: 6.9813. Min Act: -0.1700
Data Index: 6206840 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5750. Min Range: -7.5750
Max Act: 6.9813. Min Act: -0.1700
Data Index: 4023325 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5750. Min Range: -7.5750
Max Act: 6.9813. Min Act: -0.1700
Data Index: 4185195 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5750. Min Range: -7.5750
Max Act: 6.9500. Min Act: -0.1700
Data Index: 178182 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5750. Min Range: -7.5750
Max Act: 6.9500. Min Act: -0.1700
Data Index: 6206829 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5750. Min Range: -7.5750
Max Act: 6.9500. Min Act: -0.1700
Data Index: 3613537 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5750. Min Range: -7.5750
Max Act: 6.9188. Min Act: -0.1700
Data Index: 3194492 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5750. Min Range: -7.5750
Max Act: 6.9188. Min Act: -0.1700
Data Index: 3713600 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5750. Min Range: -7.5750
Max Act: 6.9188. Min Act: -0.1700
Data Index: 6206837 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5750. Min Range: -7.5750
Max Act: 6.9188. Min Act: -0.1700
Data Index: 5882471 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5750. Min Range: -7.5750
Max Act: 6.9188. Min Act: -0.1700
Data Index: 5882474 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19