Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4354 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.2515. Min Act: -0.1700
Data Index: 7457345 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.1577. Min Act: -0.1700
Data Index: 3530022 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.1264. Min Act: -0.1700
Data Index: 6191418 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.0952. Min Act: -0.1700
Data Index: 3239549 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.0639. Min Act: -0.1700
Data Index: 5456443 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.0639. Min Act: -0.1700
Data Index: 2068853 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.0014. Min Act: -0.1700
Data Index: 4878820 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2515. Min Range: -4.2515
Max Act: 4.0014. Min Act: -0.1700
Data Index: 922510 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2515. Min Range: -4.2515
Max Act: 3.9858. Min Act: -0.1700
Data Index: 5905049 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2515. Min Range: -4.2515
Max Act: 3.9858. Min Act: -0.1700
Data Index: 1668557 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2515. Min Range: -4.2515
Max Act: 3.9545. Min Act: -0.1700
Data Index: 8187283 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2515. Min Range: -4.2515
Max Act: 3.9389. Min Act: -0.1700
Data Index: 4274472 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2515. Min Range: -4.2515
Max Act: 3.9545. Min Act: -0.1700
Data Index: 3898367 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2515. Min Range: -4.2515
Max Act: 3.9076. Min Act: -0.1700
Data Index: 3235201 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2515. Min Range: -4.2515
Max Act: 3.9233. Min Act: -0.1700
Data Index: 5847669 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2515. Min Range: -4.2515
Max Act: 3.9076. Min Act: -0.1700
Data Index: 4037148 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2515. Min Range: -4.2515
Max Act: 3.8764. Min Act: -0.1700
Data Index: 511050 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2515. Min Range: -4.2515
Max Act: 3.8607. Min Act: -0.1700
Data Index: 3451561 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2515. Min Range: -4.2515
Max Act: 3.8607. Min Act: -0.1700
Data Index: 4010755 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2515. Min Range: -4.2515
Max Act: 3.8607. Min Act: -0.1700
Data Index: 8126981 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19