Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.8531. Min Act: -0.1700
Data Index: 4611202 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.7906. Min Act: -0.1700
Data Index: 8699402 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.5406. Min Act: -0.1700
Data Index: 8140915 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.5093. Min Act: -0.1700
Data Index: 951052 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.3843. Min Act: -0.1700
Data Index: 1480672 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.4156. Min Act: -0.1700
Data Index: 7385359 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.3531. Min Act: -0.1700
Data Index: 363469 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.3531. Min Act: -0.1700
Data Index: 1820465 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.3531. Min Act: -0.1700
Data Index: 140805 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.3531. Min Act: -0.1700
Data Index: 4943325 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.3531. Min Act: -0.1700
Data Index: 4936134 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.3218. Min Act: -0.1700
Data Index: 4554438 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.3218. Min Act: -0.1700
Data Index: 6779606 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.3218. Min Act: -0.1700
Data Index: 595406 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.2906. Min Act: -0.1700
Data Index: 2794737 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.2593. Min Act: -0.1700
Data Index: 1264290 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.2906. Min Act: -0.1700
Data Index: 2743952 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.2593. Min Act: -0.1700
Data Index: 1624622 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.2593. Min Act: -0.1700
Data Index: 4735390 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8531. Min Range: -5.8531
Max Act: 5.2593. Min Act: -0.1700
Data Index: 2531320 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19