Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3343 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.4475. Min Act: -0.1700
Data Index: 4789299 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.3538. Min Act: -0.1700
Data Index: 8452300 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.3225. Min Act: -0.1700
Data Index: 8637711 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.2600. Min Act: -0.1700
Data Index: 939215 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.2913. Min Act: -0.1700
Data Index: 3050196 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.2600. Min Act: -0.1700
Data Index: 5124323 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.2600. Min Act: -0.1700
Data Index: 6302242 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.2288. Min Act: -0.1700
Data Index: 55271 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.2288. Min Act: -0.1700
Data Index: 7036478 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.2288. Min Act: -0.1700
Data Index: 7654856 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.2288. Min Act: -0.1700
Data Index: 3564674 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.2288. Min Act: -0.1700
Data Index: 4998644 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.1975. Min Act: -0.1700
Data Index: 7497658 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.1975. Min Act: -0.1700
Data Index: 2068484 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.1663. Min Act: -0.1700
Data Index: 4153429 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.1663. Min Act: -0.1700
Data Index: 2398444 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.1663. Min Act: -0.1700
Data Index: 1201808 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.1350. Min Act: -0.1700
Data Index: 6759183 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.1350. Min Act: -0.1700
Data Index: 4380674 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4475. Min Range: -6.4475
Max Act: 6.1350. Min Act: -0.1700
Data Index: 6759389 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19