Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4507. Min Range: -6.4507
Max Act: 6.4507. Min Act: -0.1700
Data Index: 49132 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4507. Min Range: -6.4507
Max Act: 6.3257. Min Act: -0.1700
Data Index: 6922143 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4507. Min Range: -6.4507
Max Act: 6.2632. Min Act: -0.1700
Data Index: 4983710 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4507. Min Range: -6.4507
Max Act: 6.2632. Min Act: -0.1700
Data Index: 5224641 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4507. Min Range: -6.4507
Max Act: 6.2632. Min Act: -0.1700
Data Index: 5732771 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4507. Min Range: -6.4507
Max Act: 6.1382. Min Act: -0.1700
Data Index: 1563982 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4507. Min Range: -6.4507
Max Act: 6.1695. Min Act: -0.1700
Data Index: 2922398 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4507. Min Range: -6.4507
Max Act: 6.1695. Min Act: -0.1700
Data Index: 2786536 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4507. Min Range: -6.4507
Max Act: 6.0757. Min Act: -0.1700
Data Index: 1148320 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4507. Min Range: -6.4507
Max Act: 6.1382. Min Act: -0.1700
Data Index: 3968091 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4507. Min Range: -6.4507
Max Act: 6.0757. Min Act: -0.1700
Data Index: 5026521 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4507. Min Range: -6.4507
Max Act: 6.0757. Min Act: -0.1699
Data Index: 3494595 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4507. Min Range: -6.4507
Max Act: 6.0132. Min Act: -0.1700
Data Index: 6518675 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4507. Min Range: -6.4507
Max Act: 6.0132. Min Act: -0.1700
Data Index: 6653739 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4507. Min Range: -6.4507
Max Act: 5.9820. Min Act: -0.1700
Data Index: 251394 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4507. Min Range: -6.4507
Max Act: 5.9507. Min Act: -0.1700
Data Index: 7087051 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4507. Min Range: -6.4507
Max Act: 5.9820. Min Act: -0.1697
Data Index: 3494597 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4507. Min Range: -6.4507
Max Act: 5.9820. Min Act: -0.1700
Data Index: 3465755 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4507. Min Range: -6.4507
Max Act: 5.9507. Min Act: -0.1700
Data Index: 5965254 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4507. Min Range: -6.4507
Max Act: 5.9507. Min Act: -0.1700
Data Index: 2593042 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19