Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4720 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1040. Min Range: -5.1040
Max Act: 5.1040. Min Act: -0.1700
Data Index: 315860 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1040. Min Range: -5.1040
Max Act: 5.0727. Min Act: -0.1700
Data Index: 2837074 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1040. Min Range: -5.1040
Max Act: 5.0727. Min Act: -0.1700
Data Index: 6642674 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1040. Min Range: -5.1040
Max Act: 4.9477. Min Act: -0.1700
Data Index: 1015321 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1040. Min Range: -5.1040
Max Act: 4.9477. Min Act: -0.1700
Data Index: 8553276 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1040. Min Range: -5.1040
Max Act: 4.8852. Min Act: -0.1700
Data Index: 1712793 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1040. Min Range: -5.1040
Max Act: 4.7915. Min Act: -0.1700
Data Index: 1564068 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1040. Min Range: -5.1040
Max Act: 4.7915. Min Act: -0.1700
Data Index: 3916533 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1040. Min Range: -5.1040
Max Act: 4.7602. Min Act: -0.1700
Data Index: 6623462 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1040. Min Range: -5.1040
Max Act: 4.7602. Min Act: -0.1700
Data Index: 1633096 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1040. Min Range: -5.1040
Max Act: 4.6977. Min Act: -0.1700
Data Index: 5688308 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1040. Min Range: -5.1040
Max Act: 4.6352. Min Act: -0.1700
Data Index: 7635810 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1040. Min Range: -5.1040
Max Act: 4.6352. Min Act: -0.1700
Data Index: 2568065 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1040. Min Range: -5.1040
Max Act: 4.6040. Min Act: -0.1700
Data Index: 6623463 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1040. Min Range: -5.1040
Max Act: 4.6040. Min Act: -0.1700
Data Index: 366320 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1040. Min Range: -5.1040
Max Act: 4.6040. Min Act: -0.1700
Data Index: 8617088 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1040. Min Range: -5.1040
Max Act: 4.6352. Min Act: -0.1700
Data Index: 1908832 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1040. Min Range: -5.1040
Max Act: 4.5727. Min Act: -0.1700
Data Index: 2724536 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1040. Min Range: -5.1040
Max Act: 4.5727. Min Act: -0.1700
Data Index: 401907 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1040. Min Range: -5.1040
Max Act: 4.5727. Min Act: -0.1700
Data Index: 5723537 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19