Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4038 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.4751. Min Act: -0.1700
Data Index: 6249303 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.4439. Min Act: -0.1700
Data Index: 1651376 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.4439. Min Act: -0.1700
Data Index: 2536962 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.4126. Min Act: -0.1700
Data Index: 7559756 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.4126. Min Act: -0.1700
Data Index: 2612761 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.3814. Min Act: -0.1700
Data Index: 7241431 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.3814. Min Act: -0.1700
Data Index: 7284728 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.3501. Min Act: -0.1700
Data Index: 7241430 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.3501. Min Act: -0.1700
Data Index: 1638850 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.3501. Min Act: -0.1700
Data Index: 3667228 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.3189. Min Act: -0.1700
Data Index: 6199861 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.2876. Min Act: -0.1700
Data Index: 5128181 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.2876. Min Act: -0.1700
Data Index: 1638820 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.2876. Min Act: -0.1700
Data Index: 7597584 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.2564. Min Act: -0.1700
Data Index: 3857301 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.1939. Min Act: -0.1700
Data Index: 7378152 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.2564. Min Act: -0.1700
Data Index: 4841938 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.2251. Min Act: -0.1700
Data Index: 8530909 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.1626. Min Act: -0.1700
Data Index: 949766 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4751. Min Range: -5.4751
Max Act: 5.1939. Min Act: -0.1700
Data Index: 3876021 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19