Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4310 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2462. Min Range: -5.2462
Max Act: 5.2462. Min Act: -0.1700
Data Index: 1999628 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.8712. Min Act: -0.1700
Data Index: 1918189 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.7149. Min Act: -0.1700
Data Index: 6478217 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.7149. Min Act: -0.1700
Data Index: 5972664 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.6837. Min Act: -0.1700
Data Index: 28361 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.5587. Min Act: -0.1700
Data Index: 6753615 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.5899. Min Act: -0.1700
Data Index: 7709623 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.5899. Min Act: -0.1700
Data Index: 768007 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.5587. Min Act: -0.1700
Data Index: 5970604 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.5587. Min Act: -0.1700
Data Index: 7830412 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.5587. Min Act: -0.1700
Data Index: 4917020 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.4962. Min Act: -0.1700
Data Index: 366538 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.4649. Min Act: -0.1700
Data Index: 8116675 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.4649. Min Act: -0.1700
Data Index: 3675705 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.4649. Min Act: -0.1700
Data Index: 1176756 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.4962. Min Act: -0.1700
Data Index: 2860720 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.4649. Min Act: -0.1700
Data Index: 2887122 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.4649. Min Act: -0.1700
Data Index: 2180335 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.4337. Min Act: -0.1700
Data Index: 3323544 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.4337. Min Act: -0.1700
Data Index: 7805214 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19