Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4350 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1142. Min Range: -4.1142
Max Act: 4.1142. Min Act: -0.1700
Data Index: 2671681 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.9266. Min Act: -0.1700
Data Index: 6515285 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.8953. Min Act: -0.1700
Data Index: 6110946 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.8953. Min Act: -0.1700
Data Index: 6141421 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.8328. Min Act: -0.1700
Data Index: 3945562 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.8328. Min Act: -0.1700
Data Index: 1257384 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.7703. Min Act: -0.1700
Data Index: 1311002 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.7703. Min Act: -0.1700
Data Index: 3184346 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.7703. Min Act: -0.1700
Data Index: 1311001 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.7390. Min Act: -0.1700
Data Index: 4105032 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.7077. Min Act: -0.1700
Data Index: 866872 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.6764. Min Act: -0.1700
Data Index: 452679 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.6764. Min Act: -0.1700
Data Index: 8247070 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.6451. Min Act: -0.1700
Data Index: 6240036 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.6451. Min Act: -0.1700
Data Index: 911529 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.6451. Min Act: -0.1700
Data Index: 8352236 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.6451. Min Act: -0.1700
Data Index: 3844951 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.6451. Min Act: -0.1700
Data Index: 4507481 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.6451. Min Act: -0.1700
Data Index: 407596 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1142. Min Range: -4.1142
Max Act: 3.6138. Min Act: -0.1700
Data Index: 196534 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19