Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1584 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.5157. Min Range: -9.5157
Max Act: 9.5157. Min Act: -0.1700
Data Index: 3698115 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5157. Min Range: -9.5157
Max Act: 9.1407. Min Act: -0.1700
Data Index: 1297007 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5157. Min Range: -9.5157
Max Act: 8.8907. Min Act: -0.1700
Data Index: 2992262 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5157. Min Range: -9.5157
Max Act: 8.8282. Min Act: -0.1700
Data Index: 966975 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5157. Min Range: -9.5157
Max Act: 8.7032. Min Act: -0.1700
Data Index: 6978006 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5157. Min Range: -9.5157
Max Act: 8.6407. Min Act: -0.1700
Data Index: 3749142 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5157. Min Range: -9.5157
Max Act: 8.5782. Min Act: -0.1700
Data Index: 1914807 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5157. Min Range: -9.5157
Max Act: 8.5157. Min Act: -0.1700
Data Index: 4555413 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5157. Min Range: -9.5157
Max Act: 8.5157. Min Act: -0.1700
Data Index: 6303032 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5157. Min Range: -9.5157
Max Act: 8.4532. Min Act: -0.1700
Data Index: 6467425 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5157. Min Range: -9.5157
Max Act: 8.5157. Min Act: -0.1700
Data Index: 4093713 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5157. Min Range: -9.5157
Max Act: 8.3282. Min Act: -0.1700
Data Index: 2915214 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5157. Min Range: -9.5157
Max Act: 8.3907. Min Act: -0.1700
Data Index: 1068418 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5157. Min Range: -9.5157
Max Act: 8.0782. Min Act: -0.1700
Data Index: 6795794 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5157. Min Range: -9.5157
Max Act: 8.0782. Min Act: -0.1700
Data Index: 4674861 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5157. Min Range: -9.5157
Max Act: 8.0782. Min Act: -0.1700
Data Index: 1787337 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5157. Min Range: -9.5157
Max Act: 7.9844. Min Act: -0.1700
Data Index: 8719455 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5157. Min Range: -9.5157
Max Act: 8.0157. Min Act: -0.1700
Data Index: 192832 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5157. Min Range: -9.5157
Max Act: 7.8594. Min Act: -0.1700
Data Index: 7151880 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5157. Min Range: -9.5157
Max Act: 7.8594. Min Act: -0.1700
Data Index: 4102332 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19