Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1963 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6962. Min Act: -0.1233
Data Index: 1378989 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1458
Data Index: 3553277 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1342
Data Index: 7374436 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1602
Data Index: 6310722 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1368
Data Index: 6145387 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1580
Data Index: 5912979 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1448
Data Index: 5046883 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1204
Data Index: 4811789 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1565
Data Index: 4315405 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1620
Data Index: 4126368 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1216
Data Index: 3863390 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1693
Data Index: 550518 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1675
Data Index: 3530979 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1662
Data Index: 3398673 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1540
Data Index: 3057244 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1257
Data Index: 2839531 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1700
Data Index: 7529716 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.0890
Data Index: 1997366 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1339
Data Index: 1350987 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6962. Min Range: -2.6962
Max Act: 2.6321. Min Act: -0.1696
Data Index: 1291924 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19