Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.7580. Min Act: -0.1700
Data Index: 4894533 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.6954. Min Act: -0.1700
Data Index: 7476217 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.6329. Min Act: -0.1700
Data Index: 6746069 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.5859. Min Act: -0.1700
Data Index: 2219581 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.5859. Min Act: -0.1700
Data Index: 4588712 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.5859. Min Act: -0.1700
Data Index: 7581350 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.5703. Min Act: -0.1700
Data Index: 1549229 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.5703. Min Act: -0.1700
Data Index: 4264974 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.5546. Min Act: -0.1700
Data Index: 7425438 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.5703. Min Act: -0.1700
Data Index: 8374609 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.5389. Min Act: -0.1700
Data Index: 3256906 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.5389. Min Act: -0.1700
Data Index: 4182982 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.5233. Min Act: -0.1700
Data Index: 8642937 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.5233. Min Act: -0.1700
Data Index: 2099694 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.5076. Min Act: -0.1700
Data Index: 5510578 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.5076. Min Act: -0.1700
Data Index: 3684711 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.5076. Min Act: -0.1700
Data Index: 950731 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.4920. Min Act: -0.1700
Data Index: 892166 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.4763. Min Act: -0.1700
Data Index: 2638950 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7580. Min Range: -3.7580
Max Act: 3.4920. Min Act: -0.1700
Data Index: 1248712 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19