Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2470 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4874. Min Range: -6.4874
Max Act: 6.4874. Min Act: -0.1700
Data Index: 8685410 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4874. Min Range: -6.4874
Max Act: 6.3624. Min Act: -0.1700
Data Index: 4747657 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4874. Min Range: -6.4874
Max Act: 6.2686. Min Act: -0.1700
Data Index: 2635348 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4874. Min Range: -6.4874
Max Act: 6.2374. Min Act: -0.1700
Data Index: 7658350 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4874. Min Range: -6.4874
Max Act: 6.1749. Min Act: -0.1700
Data Index: 8521153 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4874. Min Range: -6.4874
Max Act: 6.1749. Min Act: -0.1700
Data Index: 8734725 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4874. Min Range: -6.4874
Max Act: 6.1749. Min Act: -0.1700
Data Index: 1428899 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4874. Min Range: -6.4874
Max Act: 6.1436. Min Act: -0.1700
Data Index: 3206483 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4874. Min Range: -6.4874
Max Act: 6.1436. Min Act: -0.1700
Data Index: 8603768 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4874. Min Range: -6.4874
Max Act: 6.1436. Min Act: -0.1700
Data Index: 8529598 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4874. Min Range: -6.4874
Max Act: 6.0811. Min Act: -0.1700
Data Index: 2575099 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4874. Min Range: -6.4874
Max Act: 6.0499. Min Act: -0.1700
Data Index: 2492426 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4874. Min Range: -6.4874
Max Act: 6.0499. Min Act: -0.1700
Data Index: 1522685 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4874. Min Range: -6.4874
Max Act: 6.0499. Min Act: -0.1700
Data Index: 1235901 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4874. Min Range: -6.4874
Max Act: 6.0186. Min Act: -0.1700
Data Index: 7817753 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4874. Min Range: -6.4874
Max Act: 5.9874. Min Act: -0.1700
Data Index: 8741344 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4874. Min Range: -6.4874
Max Act: 5.9561. Min Act: -0.1700
Data Index: 1993092 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4874. Min Range: -6.4874
Max Act: 5.9561. Min Act: -0.1700
Data Index: 8496770 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4874. Min Range: -6.4874
Max Act: 5.9561. Min Act: -0.1700
Data Index: 2133912 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4874. Min Range: -6.4874
Max Act: 5.9249. Min Act: -0.1700
Data Index: 1210920 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19