Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2150 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.8857. Min Act: -0.1700
Data Index: 4236912 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.7742. Min Act: -0.1696
Data Index: 41938 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.7656. Min Act: -0.1699
Data Index: 3214906 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.7570. Min Act: -0.1700
Data Index: 4781840 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.7397. Min Act: -0.1699
Data Index: 6184170 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.7397. Min Act: -0.1699
Data Index: 6976137 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.6964. Min Act: -0.1700
Data Index: 4725081 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.7051. Min Act: -0.1699
Data Index: 6996317 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.6964. Min Act: -0.1699
Data Index: 3540904 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.6616. Min Act: -0.1700
Data Index: 4150311 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.6616. Min Act: -0.1700
Data Index: 5620698 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.6703. Min Act: -0.1697
Data Index: 291258 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.6616. Min Act: -0.1700
Data Index: 8373587 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.6616. Min Act: -0.1699
Data Index: 415610 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.6529. Min Act: -0.1700
Data Index: 994619 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.6529. Min Act: -0.1700
Data Index: 2278816 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.6442. Min Act: -0.1700
Data Index: 3013935 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.6355. Min Act: -0.1699
Data Index: 1726656 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.6355. Min Act: -0.1475
Data Index: 2269342 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8857. Min Range: -1.8857
Max Act: 1.6268. Min Act: -0.1697
Data Index: 6096864 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19