Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5467 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2393. Min Range: -9.2393
Max Act: 9.2393. Min Act: -0.1700
Data Index: 4707599 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.4893. Min Act: -0.1700
Data Index: 6277766 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.4268. Min Act: -0.1700
Data Index: 7143631 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.4893. Min Act: -0.1700
Data Index: 7900641 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.4268. Min Act: -0.1700
Data Index: 1082595 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.3643. Min Act: -0.1700
Data Index: 5822504 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.3018. Min Act: -0.1700
Data Index: 6892413 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.2706. Min Act: -0.1700
Data Index: 2221010 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.2706. Min Act: -0.1700
Data Index: 2419326 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.2081. Min Act: -0.1700
Data Index: 88076 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.2706. Min Act: -0.1700
Data Index: 8427933 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.1143. Min Act: -0.1700
Data Index: 5932300 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.0831. Min Act: -0.1700
Data Index: 6050362 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.0831. Min Act: -0.1700
Data Index: 7355669 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.0831. Min Act: -0.1700
Data Index: 4891605 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.0518. Min Act: -0.1700
Data Index: 1209601 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.0831. Min Act: -0.1700
Data Index: 1139073 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.0518. Min Act: -0.1700
Data Index: 1244398 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.0831. Min Act: -0.1700
Data Index: 5852515 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2393. Min Range: -9.2393
Max Act: 8.0518. Min Act: -0.1700
Data Index: 7026332 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19