Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3563 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.6172. Min Act: -0.1700
Data Index: 6550500 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.5859. Min Act: -0.1700
Data Index: 8229840 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.5547. Min Act: -0.1700
Data Index: 3843660 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.5547. Min Act: -0.1700
Data Index: 4434394 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.4922. Min Act: -0.1700
Data Index: 4492466 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.3672. Min Act: -0.1700
Data Index: 2394319 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.3672. Min Act: -0.1700
Data Index: 5389158 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.3047. Min Act: -0.1700
Data Index: 3583117 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.3359. Min Act: -0.1700
Data Index: 3295173 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.3047. Min Act: -0.1700
Data Index: 740453 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.3047. Min Act: -0.1700
Data Index: 3573116 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.3047. Min Act: -0.1700
Data Index: 6485232 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.3047. Min Act: -0.1700
Data Index: 6122707 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.3359. Min Act: -0.1700
Data Index: 398209 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.2734. Min Act: -0.1700
Data Index: 3890091 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.3047. Min Act: -0.1700
Data Index: 5891074 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.2734. Min Act: -0.1700
Data Index: 6550496 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.2734. Min Act: -0.1700
Data Index: 4639829 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.2422. Min Act: -0.1700
Data Index: 4418765 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6172. Min Range: -6.6172
Max Act: 6.2422. Min Act: -0.1700
Data Index: 4580732 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19