Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1958 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1271. Min Range: -4.1271
Max Act: 4.1271. Min Act: -0.1700
Data Index: 2408467 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1271. Min Range: -4.1271
Max Act: 4.0646. Min Act: -0.1700
Data Index: 7730191 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1271. Min Range: -4.1271
Max Act: 4.0646. Min Act: -0.1700
Data Index: 7590675 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1271. Min Range: -4.1271
Max Act: 3.9708. Min Act: -0.1700
Data Index: 2960025 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1271. Min Range: -4.1271
Max Act: 3.9708. Min Act: -0.1700
Data Index: 7683662 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1271. Min Range: -4.1271
Max Act: 3.9395. Min Act: -0.1700
Data Index: 900552 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1271. Min Range: -4.1271
Max Act: 3.9708. Min Act: -0.1700
Data Index: 5182573 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1271. Min Range: -4.1271
Max Act: 3.9395. Min Act: -0.1700
Data Index: 3572156 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1271. Min Range: -4.1271
Max Act: 3.9395. Min Act: -0.1700
Data Index: 4620317 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1271. Min Range: -4.1271
Max Act: 3.9083. Min Act: -0.1700
Data Index: 679744 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1271. Min Range: -4.1271
Max Act: 3.9083. Min Act: -0.1700
Data Index: 4363151 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1271. Min Range: -4.1271
Max Act: 3.9083. Min Act: -0.1700
Data Index: 514469 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1271. Min Range: -4.1271
Max Act: 3.9083. Min Act: -0.1700
Data Index: 4317411 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1271. Min Range: -4.1271
Max Act: 3.9083. Min Act: -0.1700
Data Index: 4898994 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1271. Min Range: -4.1271
Max Act: 3.9083. Min Act: -0.1700
Data Index: 3479532 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1271. Min Range: -4.1271
Max Act: 3.9083. Min Act: -0.1700
Data Index: 4037356 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1271. Min Range: -4.1271
Max Act: 3.9083. Min Act: -0.1700
Data Index: 4943731 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1271. Min Range: -4.1271
Max Act: 3.9083. Min Act: -0.1700
Data Index: 6676032 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1271. Min Range: -4.1271
Max Act: 3.8770. Min Act: -0.1700
Data Index: 1147890 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1271. Min Range: -4.1271
Max Act: 3.8770. Min Act: -0.1700
Data Index: 6274846 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19