Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5899 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.8023. Min Act: -0.1700
Data Index: 5570410 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.5210. Min Act: -0.1700
Data Index: 342953 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.4898. Min Act: -0.1700
Data Index: 6025625 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.4898. Min Act: -0.1700
Data Index: 6965469 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.4273. Min Act: -0.1700
Data Index: 8748900 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.3648. Min Act: -0.1700
Data Index: 454088 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.3960. Min Act: -0.1700
Data Index: 4522719 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.3960. Min Act: -0.1700
Data Index: 1724058 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.3960. Min Act: -0.1700
Data Index: 7037176 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.3960. Min Act: -0.1700
Data Index: 6950359 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.3960. Min Act: -0.1700
Data Index: 2713457 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.3648. Min Act: -0.1700
Data Index: 415537 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.3648. Min Act: -0.1700
Data Index: 3469002 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.3023. Min Act: -0.1700
Data Index: 5709130 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.2710. Min Act: -0.1700
Data Index: 3241519 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.2710. Min Act: -0.1700
Data Index: 4865682 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.2710. Min Act: -0.1700
Data Index: 6751882 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.2398. Min Act: -0.1700
Data Index: 759212 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.2398. Min Act: -0.1700
Data Index: 4634437 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8023. Min Range: -5.8023
Max Act: 5.2398. Min Act: -0.1700
Data Index: 4573269 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19