Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 309 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.3747. Min Range: -9.3747
Max Act: 9.3747. Min Act: -0.1700
Data Index: 502364 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3747. Min Range: -9.3747
Max Act: 9.3122. Min Act: -0.1700
Data Index: 1004 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3747. Min Range: -9.3747
Max Act: 9.2497. Min Act: -0.1700
Data Index: 963778 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3747. Min Range: -9.3747
Max Act: 9.1872. Min Act: -0.1700
Data Index: 7700609 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3747. Min Range: -9.3747
Max Act: 9.1247. Min Act: -0.1700
Data Index: 725803 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3747. Min Range: -9.3747
Max Act: 9.0622. Min Act: -0.1700
Data Index: 2759428 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3747. Min Range: -9.3747
Max Act: 9.1247. Min Act: -0.1700
Data Index: 8372015 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3747. Min Range: -9.3747
Max Act: 8.9997. Min Act: -0.1700
Data Index: 2255883 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3747. Min Range: -9.3747
Max Act: 9.0622. Min Act: -0.1700
Data Index: 4134370 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3747. Min Range: -9.3747
Max Act: 8.9997. Min Act: -0.1700
Data Index: 8466536 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3747. Min Range: -9.3747
Max Act: 8.9997. Min Act: -0.1700
Data Index: 5144244 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3747. Min Range: -9.3747
Max Act: 8.8747. Min Act: -0.1700
Data Index: 6404907 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3747. Min Range: -9.3747
Max Act: 8.8747. Min Act: -0.1700
Data Index: 485860 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3747. Min Range: -9.3747
Max Act: 8.9372. Min Act: -0.1700
Data Index: 1084684 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3747. Min Range: -9.3747
Max Act: 8.9997. Min Act: -0.1700
Data Index: 7188162 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3747. Min Range: -9.3747
Max Act: 8.9372. Min Act: -0.1700
Data Index: 1735330 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3747. Min Range: -9.3747
Max Act: 8.9372. Min Act: -0.1700
Data Index: 3844424 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3747. Min Range: -9.3747
Max Act: 8.8747. Min Act: -0.1700
Data Index: 1389463 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3747. Min Range: -9.3747
Max Act: 8.8122. Min Act: -0.1700
Data Index: 7338433 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3747. Min Range: -9.3747
Max Act: 8.8747. Min Act: -0.1700
Data Index: 8130834 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19