Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2886 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1672. Min Range: -7.1672
Max Act: 7.1672. Min Act: -0.1700
Data Index: 3479473 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1672. Min Range: -7.1672
Max Act: 7.1360. Min Act: -0.1700
Data Index: 3479471 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.9485. Min Act: -0.1700
Data Index: 4693022 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.8860. Min Act: -0.1700
Data Index: 2833405 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.9172. Min Act: -0.1700
Data Index: 531851 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.8235. Min Act: -0.1700
Data Index: 5195329 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.7922. Min Act: -0.1700
Data Index: 6848813 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.7922. Min Act: -0.1700
Data Index: 381873 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.7922. Min Act: -0.1700
Data Index: 7471962 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.7610. Min Act: -0.1700
Data Index: 285910 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.7610. Min Act: -0.1700
Data Index: 1750335 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.7297. Min Act: -0.1700
Data Index: 5453582 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.6985. Min Act: -0.1700
Data Index: 8713610 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.6360. Min Act: -0.1700
Data Index: 7676672 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.6047. Min Act: -0.1700
Data Index: 8320603 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.6047. Min Act: -0.1700
Data Index: 6040528 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.5735. Min Act: -0.1700
Data Index: 5824455 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.5735. Min Act: -0.1700
Data Index: 6502859 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.5735. Min Act: -0.1700
Data Index: 3714418 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1672. Min Range: -7.1672
Max Act: 6.5422. Min Act: -0.1700
Data Index: 2178067 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19