Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2148 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.6773. Min Act: -0.1700
Data Index: 422933 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.6148. Min Act: -0.1669
Data Index: 1955086 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.5523. Min Act: -0.1691
Data Index: 7062074 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.3648. Min Act: -0.1698
Data Index: 1097208 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.3023. Min Act: -0.1700
Data Index: 8248411 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.3648. Min Act: -0.1692
Data Index: 6619229 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.3023. Min Act: -0.1700
Data Index: 8216395 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.3023. Min Act: -0.1603
Data Index: 7993670 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.3023. Min Act: -0.1697
Data Index: 4564052 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.2398. Min Act: -0.1676
Data Index: 37977 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.1773. Min Act: -0.1699
Data Index: 8592897 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.1773. Min Act: -0.1699
Data Index: 7506281 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.1148. Min Act: -0.1699
Data Index: 117286 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.1148. Min Act: -0.1332
Data Index: 4031725 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.1148. Min Act: -0.1694
Data Index: 7906501 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.1148. Min Act: -0.1699
Data Index: 6746218 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.1148. Min Act: -0.1700
Data Index: 6787064 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.1148. Min Act: -0.0394
Data Index: 3622234 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6773. Min Range: -8.6773
Max Act: 8.0523. Min Act: -0.1698
Data Index: 3450001 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6773. Min Range: -8.6773
Max Act: 7.9898. Min Act: -0.1700
Data Index: 709999 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19