Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1075 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0830. Min Range: -8.0830
Max Act: 8.0830. Min Act: -0.1700
Data Index: 1248571 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0830. Min Range: -8.0830
Max Act: 8.0518. Min Act: -0.1700
Data Index: 5439802 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.9893. Min Act: -0.1700
Data Index: 7501789 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.9268. Min Act: -0.1700
Data Index: 191660 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.8955. Min Act: -0.1700
Data Index: 7951291 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.8330. Min Act: -0.1700
Data Index: 2001639 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.8643. Min Act: -0.1700
Data Index: 2467348 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.8955. Min Act: -0.1700
Data Index: 826848 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.8018. Min Act: -0.1700
Data Index: 823792 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.8018. Min Act: -0.1700
Data Index: 4195445 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.7705. Min Act: -0.1700
Data Index: 2424486 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.7705. Min Act: -0.1700
Data Index: 2993687 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.7705. Min Act: -0.1700
Data Index: 6957522 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.7705. Min Act: -0.1700
Data Index: 8013705 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.7393. Min Act: -0.1700
Data Index: 734044 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.7080. Min Act: -0.1700
Data Index: 7268394 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.6768. Min Act: -0.1700
Data Index: 1258988 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.6768. Min Act: -0.1700
Data Index: 3618444 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.6768. Min Act: -0.1700
Data Index: 1112172 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0830. Min Range: -8.0830
Max Act: 7.6768. Min Act: -0.1700
Data Index: 7785716 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19