Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1620 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3126. Min Range: -7.3126
Max Act: 7.3126. Min Act: -0.1700
Data Index: 5120346 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3126. Min Range: -7.3126
Max Act: 7.2814. Min Act: -0.1700
Data Index: 7007755 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3126. Min Range: -7.3126
Max Act: 7.0001. Min Act: -0.1700
Data Index: 449542 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3126. Min Range: -7.3126
Max Act: 6.9689. Min Act: -0.1700
Data Index: 7097834 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3126. Min Range: -7.3126
Max Act: 6.9689. Min Act: -0.1700
Data Index: 4808828 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3126. Min Range: -7.3126
Max Act: 6.9376. Min Act: -0.1700
Data Index: 7400124 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3126. Min Range: -7.3126
Max Act: 6.9064. Min Act: -0.1700
Data Index: 89117 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3126. Min Range: -7.3126
Max Act: 6.6876. Min Act: -0.1700
Data Index: 8320942 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3126. Min Range: -7.3126
Max Act: 6.6564. Min Act: -0.1700
Data Index: 6630170 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3126. Min Range: -7.3126
Max Act: 6.5626. Min Act: -0.1700
Data Index: 4597616 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3126. Min Range: -7.3126
Max Act: 6.4376. Min Act: -0.1700
Data Index: 1621147 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3126. Min Range: -7.3126
Max Act: 6.4689. Min Act: -0.1700
Data Index: 1741036 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3126. Min Range: -7.3126
Max Act: 6.3751. Min Act: -0.1700
Data Index: 7733829 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3126. Min Range: -7.3126
Max Act: 6.4689. Min Act: -0.1700
Data Index: 750326 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3126. Min Range: -7.3126
Max Act: 6.3751. Min Act: -0.1700
Data Index: 4639826 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3126. Min Range: -7.3126
Max Act: 6.3751. Min Act: -0.1700
Data Index: 6765269 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3126. Min Range: -7.3126
Max Act: 6.3751. Min Act: -0.1700
Data Index: 6768460 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3126. Min Range: -7.3126
Max Act: 6.3751. Min Act: -0.1700
Data Index: 874968 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3126. Min Range: -7.3126
Max Act: 6.3439. Min Act: -0.1700
Data Index: 6724396 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3126. Min Range: -7.3126
Max Act: 6.3439. Min Act: -0.1700
Data Index: 4538684 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19