Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5861 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2835. Min Range: -3.2835
Max Act: 3.2835. Min Act: -0.1700
Data Index: 1925417 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.9209. Min Act: -0.1700
Data Index: 2444239 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.8574. Min Act: -0.1700
Data Index: 3124846 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.8097. Min Act: -0.1700
Data Index: 7779307 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.7779. Min Act: -0.1700
Data Index: 6985242 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.7140. Min Act: -0.1700
Data Index: 1179524 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.7140. Min Act: -0.1700
Data Index: 482914 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.7140. Min Act: -0.1700
Data Index: 3543164 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.6980. Min Act: -0.1700
Data Index: 3745915 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.6820. Min Act: -0.1700
Data Index: 4592778 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.6660. Min Act: -0.1700
Data Index: 3859022 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.6660. Min Act: -0.1700
Data Index: 4838714 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.6820. Min Act: -0.1700
Data Index: 3341515 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.6660. Min Act: -0.1700
Data Index: 4774864 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.6500. Min Act: -0.1700
Data Index: 4491634 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.6500. Min Act: -0.1700
Data Index: 7784576 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.6339. Min Act: -0.1700
Data Index: 4855514 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.6339. Min Act: -0.1700
Data Index: 3493367 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.6339. Min Act: -0.1700
Data Index: 1262624 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2835. Min Range: -3.2835
Max Act: 2.6339. Min Act: -0.1700
Data Index: 6817546 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19