Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4860 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1444. Min Range: -4.1444
Max Act: 4.1444. Min Act: -0.1700
Data Index: 2130028 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1444. Min Range: -4.1444
Max Act: 4.0506. Min Act: -0.1700
Data Index: 3870633 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.9881. Min Act: -0.1700
Data Index: 7520716 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.9568. Min Act: -0.1700
Data Index: 6120683 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.9568. Min Act: -0.1700
Data Index: 7426477 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.9568. Min Act: -0.1700
Data Index: 4538576 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.9255. Min Act: -0.1700
Data Index: 1535459 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8943. Min Act: -0.1700
Data Index: 6175201 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8943. Min Act: -0.1700
Data Index: 208058 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8943. Min Act: -0.1700
Data Index: 3883408 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8630. Min Act: -0.1700
Data Index: 8583155 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8943. Min Act: -0.1700
Data Index: 8313725 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8943. Min Act: -0.1700
Data Index: 6029772 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8943. Min Act: -0.1700
Data Index: 7719553 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8943. Min Act: -0.1700
Data Index: 5067018 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8943. Min Act: -0.1700
Data Index: 7611275 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8943. Min Act: -0.1700
Data Index: 3867968 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8943. Min Act: -0.1700
Data Index: 4480150 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8943. Min Act: -0.1700
Data Index: 6195686 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1444. Min Range: -4.1444
Max Act: 3.8630. Min Act: -0.1700
Data Index: 2377027 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19