Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 667 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.8450. Min Act: -0.1700
Data Index: 3242696 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.8279. Min Act: -0.1698
Data Index: 5657253 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.7676. Min Act: -0.1700
Data Index: 5124878 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.7590. Min Act: -0.1700
Data Index: 5070871 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.7158. Min Act: -0.1700
Data Index: 5124890 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.7244. Min Act: -0.1700
Data Index: 1108760 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.7071. Min Act: -0.1700
Data Index: 1821065 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.6898. Min Act: -0.1700
Data Index: 3266142 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.6724. Min Act: -0.1699
Data Index: 4853416 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.6811. Min Act: -0.1700
Data Index: 6630421 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.6637. Min Act: -0.1700
Data Index: 734391 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.6637. Min Act: -0.1700
Data Index: 2682969 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.6637. Min Act: -0.1700
Data Index: 8401315 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.6637. Min Act: -0.1700
Data Index: 8289060 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.6550. Min Act: -0.1698
Data Index: 8692183 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.6463. Min Act: -0.1696
Data Index: 226696 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.6637. Min Act: -0.1700
Data Index: 1261210 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.6637. Min Act: -0.1700
Data Index: 2916244 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.6376. Min Act: -0.1700
Data Index: 996366 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8450. Min Range: -1.8450
Max Act: 1.6550. Min Act: -0.1700
Data Index: 1425362 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19