Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2873 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4466. Min Range: -7.4466
Max Act: 7.4466. Min Act: -0.1700
Data Index: 3928189 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4466. Min Range: -7.4466
Max Act: 7.3216. Min Act: -0.1700
Data Index: 1870646 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4466. Min Range: -7.4466
Max Act: 7.2278. Min Act: -0.1700
Data Index: 2834923 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4466. Min Range: -7.4466
Max Act: 7.1966. Min Act: -0.1700
Data Index: 3432624 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4466. Min Range: -7.4466
Max Act: 7.1028. Min Act: -0.1700
Data Index: 1829797 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4466. Min Range: -7.4466
Max Act: 7.0403. Min Act: -0.1700
Data Index: 8620137 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4466. Min Range: -7.4466
Max Act: 6.9778. Min Act: -0.1700
Data Index: 1395587 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4466. Min Range: -7.4466
Max Act: 6.9466. Min Act: -0.1700
Data Index: 7029056 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4466. Min Range: -7.4466
Max Act: 6.9153. Min Act: -0.1700
Data Index: 6935871 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4466. Min Range: -7.4466
Max Act: 6.9466. Min Act: -0.1700
Data Index: 5494261 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4466. Min Range: -7.4466
Max Act: 6.8841. Min Act: -0.1700
Data Index: 5971803 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4466. Min Range: -7.4466
Max Act: 6.8216. Min Act: -0.1700
Data Index: 3481430 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4466. Min Range: -7.4466
Max Act: 6.8528. Min Act: -0.1700
Data Index: 8472032 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4466. Min Range: -7.4466
Max Act: 6.8216. Min Act: -0.1700
Data Index: 1276841 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4466. Min Range: -7.4466
Max Act: 6.8528. Min Act: -0.1700
Data Index: 3426894 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4466. Min Range: -7.4466
Max Act: 6.8528. Min Act: -0.1700
Data Index: 6066350 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4466. Min Range: -7.4466
Max Act: 6.8216. Min Act: -0.1700
Data Index: 1418534 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4466. Min Range: -7.4466
Max Act: 6.8216. Min Act: -0.1700
Data Index: 4120092 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4466. Min Range: -7.4466
Max Act: 6.8216. Min Act: -0.1700
Data Index: 3793559 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4466. Min Range: -7.4466
Max Act: 6.7903. Min Act: -0.1700
Data Index: 4817020 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19