Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1346 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0950. Min Range: -6.0950
Max Act: 6.0950. Min Act: -0.1700
Data Index: 8817856 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0950. Min Range: -6.0950
Max Act: 6.0325. Min Act: -0.1700
Data Index: 6461056 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0950. Min Range: -6.0950
Max Act: 6.0013. Min Act: -0.1698
Data Index: 4190378 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0950. Min Range: -6.0950
Max Act: 6.0013. Min Act: -0.1700
Data Index: 8231104 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0950. Min Range: -6.0950
Max Act: 5.9700. Min Act: -0.1700
Data Index: 6012488 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0950. Min Range: -6.0950
Max Act: 5.9388. Min Act: -0.1700
Data Index: 4562992 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0950. Min Range: -6.0950
Max Act: 5.9075. Min Act: -0.1700
Data Index: 1324888 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0950. Min Range: -6.0950
Max Act: 5.9388. Min Act: -0.1700
Data Index: 6951021 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0950. Min Range: -6.0950
Max Act: 5.9075. Min Act: -0.1700
Data Index: 7013390 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0950. Min Range: -6.0950
Max Act: 5.8763. Min Act: -0.1700
Data Index: 773328 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0950. Min Range: -6.0950
Max Act: 5.8763. Min Act: -0.1700
Data Index: 8371201 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0950. Min Range: -6.0950
Max Act: 5.8763. Min Act: -0.1700
Data Index: 3953816 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0950. Min Range: -6.0950
Max Act: 5.7825. Min Act: -0.1700
Data Index: 177363 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0950. Min Range: -6.0950
Max Act: 5.8138. Min Act: -0.1700
Data Index: 1233758 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0950. Min Range: -6.0950
Max Act: 5.8138. Min Act: -0.1700
Data Index: 2583856 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0950. Min Range: -6.0950
Max Act: 5.7825. Min Act: -0.1700
Data Index: 7876953 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0950. Min Range: -6.0950
Max Act: 5.7825. Min Act: -0.1700
Data Index: 2825408 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0950. Min Range: -6.0950
Max Act: 5.7200. Min Act: -0.1700
Data Index: 2693525 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0950. Min Range: -6.0950
Max Act: 5.7200. Min Act: -0.1700
Data Index: 3938383 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0950. Min Range: -6.0950
Max Act: 5.7200. Min Act: -0.1700
Data Index: 8605892 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19