Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3749 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3705. Min Range: -7.3705
Max Act: 7.3705. Min Act: -0.1700
Data Index: 5085960 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3705. Min Range: -7.3705
Max Act: 7.1517. Min Act: -0.1700
Data Index: 824010 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.9955. Min Act: -0.1700
Data Index: 2854087 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.8705. Min Act: -0.1700
Data Index: 7243334 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.8080. Min Act: -0.1700
Data Index: 5085961 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.8080. Min Act: -0.1700
Data Index: 4027374 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.7767. Min Act: -0.1700
Data Index: 2316947 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.7455. Min Act: -0.1700
Data Index: 1766817 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.7142. Min Act: -0.1700
Data Index: 4160483 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.6830. Min Act: -0.1700
Data Index: 7880531 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.6517. Min Act: -0.1700
Data Index: 281728 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.6517. Min Act: -0.1700
Data Index: 3473790 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.6205. Min Act: -0.1700
Data Index: 1986337 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.5892. Min Act: -0.1700
Data Index: 578809 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.5892. Min Act: -0.1700
Data Index: 8519536 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.6517. Min Act: -0.1700
Data Index: 7997723 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.5892. Min Act: -0.1700
Data Index: 5875719 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.5892. Min Act: -0.1700
Data Index: 3000571 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.5267. Min Act: -0.1700
Data Index: 1766824 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3705. Min Range: -7.3705
Max Act: 6.5580. Min Act: -0.1700
Data Index: 8562096 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19