Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4135 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.8276. Min Act: -0.1700
Data Index: 2743796 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.7963. Min Act: -0.1700
Data Index: 6404938 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.7338. Min Act: -0.1700
Data Index: 8115726 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.7338. Min Act: -0.1700
Data Index: 2055094 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.6713. Min Act: -0.1700
Data Index: 2525259 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.6401. Min Act: -0.1700
Data Index: 3160188 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.6401. Min Act: -0.1700
Data Index: 1674747 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.6088. Min Act: -0.1700
Data Index: 4699864 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.5776. Min Act: -0.1700
Data Index: 3599651 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.6401. Min Act: -0.1700
Data Index: 269913 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.6088. Min Act: -0.1700
Data Index: 227765 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.6088. Min Act: -0.1700
Data Index: 7395738 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.6088. Min Act: -0.1700
Data Index: 7981564 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.5776. Min Act: -0.1700
Data Index: 8047841 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.5463. Min Act: -0.1700
Data Index: 6446323 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.5151. Min Act: -0.1700
Data Index: 3392494 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.5463. Min Act: -0.1700
Data Index: 6183490 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.5463. Min Act: -0.1700
Data Index: 3186084 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.4838. Min Act: -0.1700
Data Index: 1147463 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8276. Min Range: -5.8276
Max Act: 5.5151. Min Act: -0.1700
Data Index: 7566678 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19