Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3603 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.5420. Min Act: -0.1700
Data Index: 4896124 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.3857. Min Act: -0.1700
Data Index: 585242 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.3232. Min Act: -0.1700
Data Index: 6482140 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.2607. Min Act: -0.1700
Data Index: 6633731 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.2607. Min Act: -0.1700
Data Index: 6983052 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.2607. Min Act: -0.1700
Data Index: 5589453 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.2295. Min Act: -0.1700
Data Index: 7411706 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.2295. Min Act: -0.1700
Data Index: 2085689 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.2295. Min Act: -0.1700
Data Index: 4732631 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.1982. Min Act: -0.1700
Data Index: 3467883 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.1982. Min Act: -0.1700
Data Index: 8043678 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.1670. Min Act: -0.1700
Data Index: 4092641 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.1357. Min Act: -0.1700
Data Index: 5839518 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.1357. Min Act: -0.1700
Data Index: 945157 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.1044. Min Act: -0.1700
Data Index: 6787844 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.1044. Min Act: -0.1700
Data Index: 2980708 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.1044. Min Act: -0.1700
Data Index: 4856085 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.1044. Min Act: -0.1700
Data Index: 3823343 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.1357. Min Act: -0.1700
Data Index: 7335017 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5420. Min Range: -4.5420
Max Act: 4.1044. Min Act: -0.1700
Data Index: 468251 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19