Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3789 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.5726. Min Act: -0.1700
Data Index: 3225003 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.3226. Min Act: -0.1700
Data Index: 6601963 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.2913. Min Act: -0.1700
Data Index: 1310369 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.2913. Min Act: -0.1700
Data Index: 5240796 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.2288. Min Act: -0.1700
Data Index: 4990347 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.2288. Min Act: -0.1700
Data Index: 4984162 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.2288. Min Act: -0.1700
Data Index: 434726 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.2288. Min Act: -0.1700
Data Index: 3060157 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.1976. Min Act: -0.1700
Data Index: 707231 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.1663. Min Act: -0.1700
Data Index: 8740983 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.1663. Min Act: -0.1700
Data Index: 2633071 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.1663. Min Act: -0.1700
Data Index: 3476257 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.1663. Min Act: -0.1700
Data Index: 1500248 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.1663. Min Act: -0.1700
Data Index: 4354907 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.1663. Min Act: -0.1700
Data Index: 8576331 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.1663. Min Act: -0.1700
Data Index: 2468550 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.1038. Min Act: -0.1700
Data Index: 7342078 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.1351. Min Act: -0.1700
Data Index: 7820622 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.1038. Min Act: -0.1700
Data Index: 4758234 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5726. Min Range: -6.5726
Max Act: 6.1038. Min Act: -0.1700
Data Index: 5800923 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19