Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2558 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3513. Min Range: -6.3513
Max Act: 6.3513. Min Act: -0.1700
Data Index: 2709854 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3513. Min Range: -6.3513
Max Act: 5.2888. Min Act: -0.1700
Data Index: 3417631 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3513. Min Range: -6.3513
Max Act: 5.2575. Min Act: -0.1700
Data Index: 2462897 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3513. Min Range: -6.3513
Max Act: 5.1638. Min Act: -0.1700
Data Index: 4936575 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3513. Min Range: -6.3513
Max Act: 5.1638. Min Act: -0.1700
Data Index: 8077857 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3513. Min Range: -6.3513
Max Act: 5.1638. Min Act: -0.1700
Data Index: 6497045 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3513. Min Range: -6.3513
Max Act: 5.1638. Min Act: -0.1700
Data Index: 368203 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3513. Min Range: -6.3513
Max Act: 5.1325. Min Act: -0.1700
Data Index: 5394277 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3513. Min Range: -6.3513
Max Act: 5.1325. Min Act: -0.1700
Data Index: 6722741 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3513. Min Range: -6.3513
Max Act: 5.1013. Min Act: -0.1700
Data Index: 6390674 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3513. Min Range: -6.3513
Max Act: 5.1013. Min Act: -0.1700
Data Index: 1788944 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3513. Min Range: -6.3513
Max Act: 5.1013. Min Act: -0.1700
Data Index: 3237222 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3513. Min Range: -6.3513
Max Act: 5.0700. Min Act: -0.1700
Data Index: 1327834 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3513. Min Range: -6.3513
Max Act: 5.0388. Min Act: -0.1700
Data Index: 7879801 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3513. Min Range: -6.3513
Max Act: 5.0075. Min Act: -0.1700
Data Index: 1816922 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3513. Min Range: -6.3513
Max Act: 5.0075. Min Act: -0.1700
Data Index: 6134503 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3513. Min Range: -6.3513
Max Act: 4.9763. Min Act: -0.1700
Data Index: 30943 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3513. Min Range: -6.3513
Max Act: 5.0075. Min Act: -0.1700
Data Index: 1790326 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3513. Min Range: -6.3513
Max Act: 4.9763. Min Act: -0.1700
Data Index: 3421542 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3513. Min Range: -6.3513
Max Act: 4.9763. Min Act: -0.1700
Data Index: 4258798 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19