Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2025 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2194. Min Range: -7.2194
Max Act: 7.2194. Min Act: -0.1700
Data Index: 7489008 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2194. Min Range: -7.2194
Max Act: 7.1882. Min Act: -0.1700
Data Index: 4906464 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2194. Min Range: -7.2194
Max Act: 7.1257. Min Act: -0.1700
Data Index: 3216359 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2194. Min Range: -7.2194
Max Act: 7.0944. Min Act: -0.1700
Data Index: 4188543 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2194. Min Range: -7.2194
Max Act: 7.0319. Min Act: -0.1700
Data Index: 4351594 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2194. Min Range: -7.2194
Max Act: 7.0632. Min Act: -0.1700
Data Index: 7777479 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2194. Min Range: -7.2194
Max Act: 6.9694. Min Act: -0.1700
Data Index: 7140428 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2194. Min Range: -7.2194
Max Act: 6.9694. Min Act: -0.1700
Data Index: 1707319 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2194. Min Range: -7.2194
Max Act: 6.9694. Min Act: -0.1700
Data Index: 7816304 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2194. Min Range: -7.2194
Max Act: 6.9382. Min Act: -0.1700
Data Index: 3865239 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2194. Min Range: -7.2194
Max Act: 6.9382. Min Act: -0.1700
Data Index: 3922717 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2194. Min Range: -7.2194
Max Act: 6.9694. Min Act: -0.1700
Data Index: 943528 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2194. Min Range: -7.2194
Max Act: 6.9069. Min Act: -0.1700
Data Index: 3019914 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2194. Min Range: -7.2194
Max Act: 6.9069. Min Act: -0.1700
Data Index: 3206898 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2194. Min Range: -7.2194
Max Act: 6.8757. Min Act: -0.1700
Data Index: 6678145 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2194. Min Range: -7.2194
Max Act: 6.9382. Min Act: -0.1700
Data Index: 8094539 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2194. Min Range: -7.2194
Max Act: 6.9069. Min Act: -0.1700
Data Index: 5663008 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2194. Min Range: -7.2194
Max Act: 6.9069. Min Act: -0.1700
Data Index: 3082495 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2194. Min Range: -7.2194
Max Act: 6.9382. Min Act: -0.1700
Data Index: 5884445 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2194. Min Range: -7.2194
Max Act: 6.9069. Min Act: -0.1700
Data Index: 748295 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19