Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4164 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.9645. Min Act: -0.1700
Data Index: 428684 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.7145. Min Act: -0.1700
Data Index: 4759926 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.6833. Min Act: -0.1700
Data Index: 7490377 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.5583. Min Act: -0.1700
Data Index: 7901867 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.5583. Min Act: -0.1700
Data Index: 5840722 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.4958. Min Act: -0.1700
Data Index: 7599600 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.4958. Min Act: -0.1700
Data Index: 7686910 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.4645. Min Act: -0.1700
Data Index: 717420 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.4020. Min Act: -0.1700
Data Index: 4892413 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.4333. Min Act: -0.1700
Data Index: 5920756 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.4020. Min Act: -0.1700
Data Index: 2286582 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.4020. Min Act: -0.1700
Data Index: 1788036 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.3708. Min Act: -0.1700
Data Index: 5611942 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.3708. Min Act: -0.1700
Data Index: 1314189 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.4020. Min Act: -0.1700
Data Index: 6271362 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.3708. Min Act: -0.1700
Data Index: 8827473 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.3395. Min Act: -0.1700
Data Index: 5117233 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.3083. Min Act: -0.1700
Data Index: 4402723 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.3083. Min Act: -0.1700
Data Index: 6536804 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9645. Min Range: -7.9645
Max Act: 7.2770. Min Act: -0.1700
Data Index: 4700088 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19