Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.8650. Min Act: -0.1700
Data Index: 4124985 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.8650. Min Act: -0.1700
Data Index: 7576262 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.7712. Min Act: -0.1700
Data Index: 1388694 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.7087. Min Act: -0.1700
Data Index: 8236086 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.7400. Min Act: -0.1700
Data Index: 5064178 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.7087. Min Act: -0.1700
Data Index: 3966293 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.6775. Min Act: -0.1700
Data Index: 3186229 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.6462. Min Act: -0.1700
Data Index: 6556536 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.6462. Min Act: -0.1700
Data Index: 2600970 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.6150. Min Act: -0.1700
Data Index: 5292776 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.6150. Min Act: -0.1700
Data Index: 3168900 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.6150. Min Act: -0.1700
Data Index: 5097271 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.5837. Min Act: -0.1700
Data Index: 3281965 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.5525. Min Act: -0.1700
Data Index: 5168060 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.5525. Min Act: -0.1700
Data Index: 190164 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.5525. Min Act: -0.1700
Data Index: 2891617 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.5212. Min Act: -0.1700
Data Index: 4563273 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.5212. Min Act: -0.1700
Data Index: 8654048 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.4900. Min Act: -0.1700
Data Index: 6216462 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8650. Min Range: -4.8650
Max Act: 4.4900. Min Act: -0.1700
Data Index: 7589028 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19