Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6374 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.5551. Min Act: -0.1700
Data Index: 1730242 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.4768. Min Act: -0.1700
Data Index: 4567545 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.4925. Min Act: -0.1700
Data Index: 3142354 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.3043. Min Act: -0.1700
Data Index: 2498290 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.2729. Min Act: -0.1700
Data Index: 1325877 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.2572. Min Act: -0.1700
Data Index: 1165265 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.2415. Min Act: -0.1700
Data Index: 538845 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.2258. Min Act: -0.1700
Data Index: 2026564 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.2101. Min Act: -0.1700
Data Index: 111044 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.2258. Min Act: -0.1700
Data Index: 4643704 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.1943. Min Act: -0.1700
Data Index: 3142352 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.2101. Min Act: -0.1700
Data Index: 5534222 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.2258. Min Act: -0.1700
Data Index: 2532043 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.2258. Min Act: -0.1700
Data Index: 4812684 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.1786. Min Act: -0.1700
Data Index: 6401477 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.2101. Min Act: -0.1700
Data Index: 4759300 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.1629. Min Act: -0.1700
Data Index: 7013076 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.1629. Min Act: -0.1700
Data Index: 5573219 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.1471. Min Act: -0.1700
Data Index: 3868377 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5551. Min Range: -3.5551
Max Act: 3.1471. Min Act: -0.1700
Data Index: 7993656 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19