Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3764 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2594. Min Range: -5.2594
Max Act: 5.2594. Min Act: -0.1700
Data Index: 4629896 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2594. Min Range: -5.2594
Max Act: 5.2281. Min Act: -0.1700
Data Index: 8060408 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2594. Min Range: -5.2594
Max Act: 5.1031. Min Act: -0.1700
Data Index: 3803516 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2594. Min Range: -5.2594
Max Act: 5.0094. Min Act: -0.1700
Data Index: 5610603 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2594. Min Range: -5.2594
Max Act: 5.0094. Min Act: -0.1700
Data Index: 3221166 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2594. Min Range: -5.2594
Max Act: 4.9469. Min Act: -0.1700
Data Index: 8331638 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2594. Min Range: -5.2594
Max Act: 4.9469. Min Act: -0.1700
Data Index: 3430546 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2594. Min Range: -5.2594
Max Act: 4.9469. Min Act: -0.1700
Data Index: 2907416 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2594. Min Range: -5.2594
Max Act: 4.9469. Min Act: -0.1700
Data Index: 1765653 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2594. Min Range: -5.2594
Max Act: 4.9156. Min Act: -0.1700
Data Index: 3156055 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2594. Min Range: -5.2594
Max Act: 4.9156. Min Act: -0.1700
Data Index: 3256411 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2594. Min Range: -5.2594
Max Act: 4.9156. Min Act: -0.1700
Data Index: 835521 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2594. Min Range: -5.2594
Max Act: 4.8844. Min Act: -0.1700
Data Index: 539998 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2594. Min Range: -5.2594
Max Act: 4.8531. Min Act: -0.1700
Data Index: 5630790 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2594. Min Range: -5.2594
Max Act: 4.8844. Min Act: -0.1700
Data Index: 8308998 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2594. Min Range: -5.2594
Max Act: 4.8844. Min Act: -0.1700
Data Index: 7920485 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2594. Min Range: -5.2594
Max Act: 4.8844. Min Act: -0.1700
Data Index: 411420 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2594. Min Range: -5.2594
Max Act: 4.8844. Min Act: -0.1700
Data Index: 7739487 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2594. Min Range: -5.2594
Max Act: 4.8531. Min Act: -0.1700
Data Index: 3433665 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2594. Min Range: -5.2594
Max Act: 4.8531. Min Act: -0.1700
Data Index: 827330 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19