Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2433 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4733. Min Range: -8.4733
Max Act: 8.4733. Min Act: -0.1700
Data Index: 3292810 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4733. Min Range: -8.4733
Max Act: 8.3483. Min Act: -0.1700
Data Index: 8533492 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4733. Min Range: -8.4733
Max Act: 8.0358. Min Act: -0.1700
Data Index: 7161803 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4733. Min Range: -8.4733
Max Act: 7.9733. Min Act: -0.1700
Data Index: 2526984 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4733. Min Range: -8.4733
Max Act: 7.9108. Min Act: -0.1700
Data Index: 3078446 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4733. Min Range: -8.4733
Max Act: 7.9108. Min Act: -0.1700
Data Index: 5666422 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4733. Min Range: -8.4733
Max Act: 7.8483. Min Act: -0.1700
Data Index: 6004681 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4733. Min Range: -8.4733
Max Act: 7.8483. Min Act: -0.1700
Data Index: 6008774 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4733. Min Range: -8.4733
Max Act: 7.8483. Min Act: -0.1700
Data Index: 2217881 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4733. Min Range: -8.4733
Max Act: 7.8483. Min Act: -0.1700
Data Index: 2610781 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4733. Min Range: -8.4733
Max Act: 7.8483. Min Act: -0.1700
Data Index: 5744148 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4733. Min Range: -8.4733
Max Act: 7.7858. Min Act: -0.1700
Data Index: 6198289 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4733. Min Range: -8.4733
Max Act: 7.7858. Min Act: -0.1700
Data Index: 8481437 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4733. Min Range: -8.4733
Max Act: 7.7233. Min Act: -0.1700
Data Index: 1048066 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4733. Min Range: -8.4733
Max Act: 7.7858. Min Act: -0.1700
Data Index: 3403215 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4733. Min Range: -8.4733
Max Act: 7.7858. Min Act: -0.1700
Data Index: 1689051 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4733. Min Range: -8.4733
Max Act: 7.7858. Min Act: -0.1700
Data Index: 6779985 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4733. Min Range: -8.4733
Max Act: 7.7858. Min Act: -0.1700
Data Index: 8159982 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4733. Min Range: -8.4733
Max Act: 7.6920. Min Act: -0.1700
Data Index: 1840124 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4733. Min Range: -8.4733
Max Act: 7.7233. Min Act: -0.1700
Data Index: 8243941 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19