Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2344 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1684. Min Range: -6.1684
Max Act: 6.1684. Min Act: -0.1700
Data Index: 8259973 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1684. Min Range: -6.1684
Max Act: 6.0121. Min Act: -0.1700
Data Index: 5342345 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1684. Min Range: -6.1684
Max Act: 6.0121. Min Act: -0.1700
Data Index: 4794527 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1684. Min Range: -6.1684
Max Act: 6.0121. Min Act: -0.1700
Data Index: 7050595 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1684. Min Range: -6.1684
Max Act: 5.9496. Min Act: -0.1700
Data Index: 1442632 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1684. Min Range: -6.1684
Max Act: 5.8871. Min Act: -0.1700
Data Index: 5845346 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1684. Min Range: -6.1684
Max Act: 5.8559. Min Act: -0.1700
Data Index: 6723787 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1684. Min Range: -6.1684
Max Act: 5.8246. Min Act: -0.1700
Data Index: 4667960 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1684. Min Range: -6.1684
Max Act: 5.8559. Min Act: -0.1700
Data Index: 5649163 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1684. Min Range: -6.1684
Max Act: 5.8559. Min Act: -0.1700
Data Index: 8718185 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1684. Min Range: -6.1684
Max Act: 5.8559. Min Act: -0.1700
Data Index: 2211966 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1684. Min Range: -6.1684
Max Act: 5.8246. Min Act: -0.1700
Data Index: 5678027 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1684. Min Range: -6.1684
Max Act: 5.8246. Min Act: -0.1700
Data Index: 6058837 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1684. Min Range: -6.1684
Max Act: 5.8246. Min Act: -0.1700
Data Index: 5953748 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1684. Min Range: -6.1684
Max Act: 5.8246. Min Act: -0.1700
Data Index: 7152257 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1684. Min Range: -6.1684
Max Act: 5.8246. Min Act: -0.1700
Data Index: 1295080 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1684. Min Range: -6.1684
Max Act: 5.7621. Min Act: -0.1700
Data Index: 1539049 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1684. Min Range: -6.1684
Max Act: 5.7934. Min Act: -0.1700
Data Index: 3602359 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1684. Min Range: -6.1684
Max Act: 5.7934. Min Act: -0.1700
Data Index: 4145533 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1684. Min Range: -6.1684
Max Act: 5.7621. Min Act: -0.1700
Data Index: 6812832 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19