Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2059 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0619. Min Range: -7.0619
Max Act: 7.0619. Min Act: -0.1700
Data Index: 7890188 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0619. Min Range: -7.0619
Max Act: 6.4681. Min Act: -0.1700
Data Index: 7623776 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0619. Min Range: -7.0619
Max Act: 6.3431. Min Act: -0.1700
Data Index: 6845167 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0619. Min Range: -7.0619
Max Act: 6.3119. Min Act: -0.1700
Data Index: 3292269 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0619. Min Range: -7.0619
Max Act: 6.2181. Min Act: -0.1700
Data Index: 6207130 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0619. Min Range: -7.0619
Max Act: 6.2494. Min Act: -0.1700
Data Index: 3950770 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0619. Min Range: -7.0619
Max Act: 6.2494. Min Act: -0.1700
Data Index: 5728233 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0619. Min Range: -7.0619
Max Act: 6.1869. Min Act: -0.1700
Data Index: 5897128 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0619. Min Range: -7.0619
Max Act: 6.1869. Min Act: -0.1700
Data Index: 8787767 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0619. Min Range: -7.0619
Max Act: 6.0931. Min Act: -0.1700
Data Index: 4793348 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0619. Min Range: -7.0619
Max Act: 6.0931. Min Act: -0.1700
Data Index: 7767892 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0619. Min Range: -7.0619
Max Act: 6.0931. Min Act: -0.1700
Data Index: 2907655 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0619. Min Range: -7.0619
Max Act: 6.0619. Min Act: -0.1700
Data Index: 32708 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0619. Min Range: -7.0619
Max Act: 6.0619. Min Act: -0.1700
Data Index: 180092 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0619. Min Range: -7.0619
Max Act: 6.0306. Min Act: -0.1700
Data Index: 1096105 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0619. Min Range: -7.0619
Max Act: 5.9681. Min Act: -0.1700
Data Index: 5016381 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0619. Min Range: -7.0619
Max Act: 5.9681. Min Act: -0.1700
Data Index: 3271007 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0619. Min Range: -7.0619
Max Act: 5.9681. Min Act: -0.1700
Data Index: 7365454 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0619. Min Range: -7.0619
Max Act: 5.9681. Min Act: -0.1700
Data Index: 5327676 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0619. Min Range: -7.0619
Max Act: 5.9681. Min Act: -0.1700
Data Index: 1393017 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19