Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5268 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.9018. Min Act: -0.1700
Data Index: 2658656 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.8080. Min Act: -0.1700
Data Index: 537444 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.7455. Min Act: -0.1700
Data Index: 813207 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.7143. Min Act: -0.1700
Data Index: 943537 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.6830. Min Act: -0.1700
Data Index: 3680918 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.7143. Min Act: -0.1700
Data Index: 3186005 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.6830. Min Act: -0.1700
Data Index: 3722100 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.6830. Min Act: -0.1700
Data Index: 4379639 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.6518. Min Act: -0.1700
Data Index: 6337138 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.6518. Min Act: -0.1700
Data Index: 6417318 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.6518. Min Act: -0.1700
Data Index: 3525015 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.6518. Min Act: -0.1700
Data Index: 6262885 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.6518. Min Act: -0.1700
Data Index: 7415828 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.6518. Min Act: -0.1700
Data Index: 1084403 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.6518. Min Act: -0.1700
Data Index: 4765137 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.6205. Min Act: -0.1700
Data Index: 7387127 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.6518. Min Act: -0.1700
Data Index: 7374003 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.6518. Min Act: -0.1700
Data Index: 5552349 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.6518. Min Act: -0.1700
Data Index: 3204712 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9018. Min Range: -5.9018
Max Act: 5.6830. Min Act: -0.1700
Data Index: 778769 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19