Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3399 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.2349. Min Act: -0.1700
Data Index: 6702155 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.2289. Min Act: -0.1700
Data Index: 2597092 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.2289. Min Act: -0.1700
Data Index: 137720 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.2228. Min Act: -0.1695
Data Index: 3209344 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.2109. Min Act: -0.1700
Data Index: 5887142 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.2109. Min Act: -0.1699
Data Index: 1734091 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.2050. Min Act: -0.1677
Data Index: 4576904 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.2050. Min Act: -0.1699
Data Index: 7476275 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.2050. Min Act: -0.1700
Data Index: 1872581 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.1992. Min Act: -0.1693
Data Index: 6268917 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.1992. Min Act: -0.1692
Data Index: 1770399 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.1992. Min Act: -0.1700
Data Index: 3834978 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.1992. Min Act: -0.1670
Data Index: 1291980 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.1992. Min Act: -0.1697
Data Index: 248457 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.1992. Min Act: -0.1669
Data Index: 2883204 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.1934. Min Act: -0.1688
Data Index: 2750843 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.1992. Min Act: -0.1699
Data Index: 2556056 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.1992. Min Act: -0.1669
Data Index: 2450411 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.1992. Min Act: -0.1669
Data Index: 460544 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2349. Min Range: -0.2349
Max Act: 0.1992. Min Act: -0.1700
Data Index: 359448 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19