Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2108 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2496. Min Range: -5.2496
Max Act: 5.2496. Min Act: -0.1700
Data Index: 6832514 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2496. Min Range: -5.2496
Max Act: 5.0934. Min Act: -0.1700
Data Index: 6109518 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2496. Min Range: -5.2496
Max Act: 5.1246. Min Act: -0.1700
Data Index: 498878 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2496. Min Range: -5.2496
Max Act: 5.0934. Min Act: -0.1700
Data Index: 755430 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2496. Min Range: -5.2496
Max Act: 4.9371. Min Act: -0.1700
Data Index: 2778344 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2496. Min Range: -5.2496
Max Act: 4.9683. Min Act: -0.1700
Data Index: 7081904 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2496. Min Range: -5.2496
Max Act: 4.9683. Min Act: -0.1700
Data Index: 3426745 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2496. Min Range: -5.2496
Max Act: 4.9683. Min Act: -0.1700
Data Index: 7777812 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2496. Min Range: -5.2496
Max Act: 4.9371. Min Act: -0.1700
Data Index: 8419162 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2496. Min Range: -5.2496
Max Act: 4.9371. Min Act: -0.1700
Data Index: 8617084 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2496. Min Range: -5.2496
Max Act: 4.8121. Min Act: -0.1700
Data Index: 4411760 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2496. Min Range: -5.2496
Max Act: 4.8746. Min Act: -0.1700
Data Index: 932607 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2496. Min Range: -5.2496
Max Act: 4.7808. Min Act: -0.1700
Data Index: 8157579 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2496. Min Range: -5.2496
Max Act: 4.8433. Min Act: -0.1700
Data Index: 7567319 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2496. Min Range: -5.2496
Max Act: 4.8121. Min Act: -0.1700
Data Index: 7162210 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2496. Min Range: -5.2496
Max Act: 4.7496. Min Act: -0.1700
Data Index: 3500386 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2496. Min Range: -5.2496
Max Act: 4.7808. Min Act: -0.1700
Data Index: 237217 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2496. Min Range: -5.2496
Max Act: 4.7808. Min Act: -0.1700
Data Index: 2394592 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2496. Min Range: -5.2496
Max Act: 4.7808. Min Act: -0.1700
Data Index: 2070692 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2496. Min Range: -5.2496
Max Act: 4.7808. Min Act: -0.1700
Data Index: 8409435 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19