Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3237 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1142. Min Range: -6.1142
Max Act: 6.1142. Min Act: -0.1700
Data Index: 5124427 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.9892. Min Act: -0.1700
Data Index: 1243788 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.9267. Min Act: -0.1700
Data Index: 4823139 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.8954. Min Act: -0.1700
Data Index: 270455 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.8642. Min Act: -0.1700
Data Index: 7716414 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.8329. Min Act: -0.1700
Data Index: 7177163 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.8329. Min Act: -0.1700
Data Index: 3649402 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.8017. Min Act: -0.1700
Data Index: 3906529 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.7704. Min Act: -0.1700
Data Index: 3001116 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.7704. Min Act: -0.1700
Data Index: 7913244 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.7704. Min Act: -0.1700
Data Index: 4449606 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.7392. Min Act: -0.1700
Data Index: 882532 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.7392. Min Act: -0.1700
Data Index: 8216627 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.7392. Min Act: -0.1700
Data Index: 8343503 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.7392. Min Act: -0.1700
Data Index: 3217295 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.7704. Min Act: -0.1700
Data Index: 676648 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.7704. Min Act: -0.1700
Data Index: 3838758 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.7079. Min Act: -0.1700
Data Index: 3686712 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.7392. Min Act: -0.1700
Data Index: 4491092 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.7079. Min Act: -0.1700
Data Index: 2972305 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19