Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2482 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.5477. Min Act: -0.1700
Data Index: 6560472 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.5007. Min Act: -0.1700
Data Index: 1868676 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.3596. Min Act: -0.1700
Data Index: 8029311 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.2183. Min Act: -0.1700
Data Index: 978422 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.2340. Min Act: -0.1700
Data Index: 3814728 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.1711. Min Act: -0.1700
Data Index: 5863663 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.1711. Min Act: -0.1700
Data Index: 7720499 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.2026. Min Act: -0.1700
Data Index: 4593836 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.1711. Min Act: -0.1700
Data Index: 7988727 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.1396. Min Act: -0.1700
Data Index: 7178695 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.1396. Min Act: -0.1700
Data Index: 3834769 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.1396. Min Act: -0.1700
Data Index: 3027323 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.1081. Min Act: -0.1700
Data Index: 1335360 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.1239. Min Act: -0.1700
Data Index: 2412431 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.1081. Min Act: -0.1700
Data Index: 6926629 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.1081. Min Act: -0.1700
Data Index: 3742117 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.0924. Min Act: -0.1700
Data Index: 6363091 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.0924. Min Act: -0.1700
Data Index: 6581108 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.0924. Min Act: -0.1700
Data Index: 3455586 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5477. Min Range: -3.5477
Max Act: 3.0766. Min Act: -0.1700
Data Index: 6146144 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19