Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2014 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3285. Min Range: -8.3285
Max Act: 8.3285. Min Act: -0.1700
Data Index: 4692913 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3285. Min Range: -8.3285
Max Act: 8.2035. Min Act: -0.1700
Data Index: 4143641 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3285. Min Range: -8.3285
Max Act: 8.0785. Min Act: -0.1700
Data Index: 6925877 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3285. Min Range: -8.3285
Max Act: 7.9535. Min Act: -0.1700
Data Index: 5255812 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3285. Min Range: -8.3285
Max Act: 7.9535. Min Act: -0.1700
Data Index: 948499 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3285. Min Range: -8.3285
Max Act: 7.8910. Min Act: -0.1700
Data Index: 3474136 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3285. Min Range: -8.3285
Max Act: 7.8285. Min Act: -0.1700
Data Index: 475076 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3285. Min Range: -8.3285
Max Act: 7.8285. Min Act: -0.1700
Data Index: 1254016 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3285. Min Range: -8.3285
Max Act: 7.6410. Min Act: -0.1700
Data Index: 6784522 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3285. Min Range: -8.3285
Max Act: 7.6410. Min Act: -0.1700
Data Index: 5837742 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3285. Min Range: -8.3285
Max Act: 7.5785. Min Act: -0.1700
Data Index: 4329046 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3285. Min Range: -8.3285
Max Act: 7.5785. Min Act: -0.1700
Data Index: 477428 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3285. Min Range: -8.3285
Max Act: 7.5472. Min Act: -0.1700
Data Index: 4769248 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3285. Min Range: -8.3285
Max Act: 7.5160. Min Act: -0.1700
Data Index: 6572085 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3285. Min Range: -8.3285
Max Act: 7.5160. Min Act: -0.1700
Data Index: 740470 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3285. Min Range: -8.3285
Max Act: 7.5160. Min Act: -0.1700
Data Index: 7872207 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3285. Min Range: -8.3285
Max Act: 7.4535. Min Act: -0.1700
Data Index: 6378480 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3285. Min Range: -8.3285
Max Act: 7.4847. Min Act: -0.1700
Data Index: 6076850 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3285. Min Range: -8.3285
Max Act: 7.4535. Min Act: -0.1700
Data Index: 378940 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3285. Min Range: -8.3285
Max Act: 7.4535. Min Act: -0.1700
Data Index: 2324657 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19