Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 695 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.5280. Min Act: -0.1700
Data Index: 7291210 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.5280. Min Act: -0.1700
Data Index: 6108875 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.4655. Min Act: -0.1700
Data Index: 3374353 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.4343. Min Act: -0.1700
Data Index: 3031801 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.4030. Min Act: -0.1700
Data Index: 1625917 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.3718. Min Act: -0.1700
Data Index: 5508249 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.3718. Min Act: -0.1700
Data Index: 4912978 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.3718. Min Act: -0.1700
Data Index: 1984155 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.3405. Min Act: -0.1700
Data Index: 1532802 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.3093. Min Act: -0.1700
Data Index: 5919546 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.3093. Min Act: -0.1700
Data Index: 6892484 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.3093. Min Act: -0.1700
Data Index: 8446 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.2780. Min Act: -0.1700
Data Index: 1266804 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.3093. Min Act: -0.1700
Data Index: 3374355 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.2780. Min Act: -0.1700
Data Index: 7143100 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.2468. Min Act: -0.1700
Data Index: 7223206 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.2468. Min Act: -0.1700
Data Index: 3154771 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.2468. Min Act: -0.1700
Data Index: 3370587 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.2468. Min Act: -0.1700
Data Index: 8766300 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.2468. Min Act: -0.1700
Data Index: 4703357 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19