Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3617 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3507. Min Range: -6.3507
Max Act: 6.3507. Min Act: -0.1700
Data Index: 1555189 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3507. Min Range: -6.3507
Max Act: 6.2257. Min Act: -0.1700
Data Index: 3944173 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3507. Min Range: -6.3507
Max Act: 6.2257. Min Act: -0.1700
Data Index: 1718452 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3507. Min Range: -6.3507
Max Act: 6.1632. Min Act: -0.1700
Data Index: 3114786 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3507. Min Range: -6.3507
Max Act: 6.1632. Min Act: -0.1700
Data Index: 6433146 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3507. Min Range: -6.3507
Max Act: 6.1319. Min Act: -0.1700
Data Index: 64016 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3507. Min Range: -6.3507
Max Act: 6.1007. Min Act: -0.1700
Data Index: 3012090 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3507. Min Range: -6.3507
Max Act: 6.0694. Min Act: -0.1700
Data Index: 1517537 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3507. Min Range: -6.3507
Max Act: 6.0382. Min Act: -0.1700
Data Index: 5898610 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3507. Min Range: -6.3507
Max Act: 6.0382. Min Act: -0.1700
Data Index: 318947 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3507. Min Range: -6.3507
Max Act: 6.0069. Min Act: -0.1700
Data Index: 4535427 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3507. Min Range: -6.3507
Max Act: 5.9757. Min Act: -0.1700
Data Index: 789596 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3507. Min Range: -6.3507
Max Act: 5.9444. Min Act: -0.1700
Data Index: 1468658 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3507. Min Range: -6.3507
Max Act: 5.9444. Min Act: -0.1700
Data Index: 5554776 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3507. Min Range: -6.3507
Max Act: 5.8819. Min Act: -0.1700
Data Index: 2527685 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3507. Min Range: -6.3507
Max Act: 5.9444. Min Act: -0.1700
Data Index: 967564 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3507. Min Range: -6.3507
Max Act: 5.9132. Min Act: -0.1700
Data Index: 8221797 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3507. Min Range: -6.3507
Max Act: 5.9132. Min Act: -0.1700
Data Index: 335473 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3507. Min Range: -6.3507
Max Act: 5.9132. Min Act: -0.1700
Data Index: 5410819 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3507. Min Range: -6.3507
Max Act: 5.8507. Min Act: -0.1700
Data Index: 3866191 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19