Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1967 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.9988. Min Act: -0.1700
Data Index: 6870168 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.9363. Min Act: -0.1700
Data Index: 6945425 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.9050. Min Act: -0.1700
Data Index: 4397701 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.7800. Min Act: -0.1700
Data Index: 27005 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.7800. Min Act: -0.1700
Data Index: 7860052 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.6238. Min Act: -0.1700
Data Index: 5686616 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.6238. Min Act: -0.1700
Data Index: 1475090 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.6238. Min Act: -0.1700
Data Index: 1700255 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.5925. Min Act: -0.1700
Data Index: 736770 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.5613. Min Act: -0.1700
Data Index: 6232478 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.5613. Min Act: -0.1700
Data Index: 5089276 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.5300. Min Act: -0.1700
Data Index: 6014511 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.5300. Min Act: -0.1700
Data Index: 2894576 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.5300. Min Act: -0.1700
Data Index: 5799628 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.4988. Min Act: -0.1700
Data Index: 3269670 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.4988. Min Act: -0.1700
Data Index: 3692888 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.4988. Min Act: -0.1700
Data Index: 2055476 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.4675. Min Act: -0.1700
Data Index: 5842166 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.4988. Min Act: -0.1700
Data Index: 2862292 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9988. Min Range: -6.9988
Max Act: 6.4675. Min Act: -0.1700
Data Index: 4813453 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19