Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3626 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4898. Min Range: -7.4898
Max Act: 7.4898. Min Act: -0.1700
Data Index: 4360586 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4898. Min Range: -7.4898
Max Act: 7.2710. Min Act: -0.1700
Data Index: 2596609 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4898. Min Range: -7.4898
Max Act: 7.2398. Min Act: -0.1700
Data Index: 3409484 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4898. Min Range: -7.4898
Max Act: 7.0523. Min Act: -0.1700
Data Index: 5353983 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4898. Min Range: -7.4898
Max Act: 6.9898. Min Act: -0.1700
Data Index: 5785025 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4898. Min Range: -7.4898
Max Act: 7.0210. Min Act: -0.1700
Data Index: 7931887 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4898. Min Range: -7.4898
Max Act: 6.9898. Min Act: -0.1700
Data Index: 1008445 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4898. Min Range: -7.4898
Max Act: 7.0210. Min Act: -0.1700
Data Index: 3129937 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4898. Min Range: -7.4898
Max Act: 6.9898. Min Act: -0.1700
Data Index: 470169 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4898. Min Range: -7.4898
Max Act: 6.9273. Min Act: -0.1700
Data Index: 3150300 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4898. Min Range: -7.4898
Max Act: 6.9585. Min Act: -0.1700
Data Index: 2115017 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4898. Min Range: -7.4898
Max Act: 6.9585. Min Act: -0.1700
Data Index: 1613242 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4898. Min Range: -7.4898
Max Act: 6.8960. Min Act: -0.1700
Data Index: 8543802 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4898. Min Range: -7.4898
Max Act: 6.8335. Min Act: -0.1700
Data Index: 7595786 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4898. Min Range: -7.4898
Max Act: 6.8023. Min Act: -0.1700
Data Index: 8148245 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4898. Min Range: -7.4898
Max Act: 6.8023. Min Act: -0.1700
Data Index: 3129598 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4898. Min Range: -7.4898
Max Act: 6.8023. Min Act: -0.1700
Data Index: 1167790 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4898. Min Range: -7.4898
Max Act: 6.8335. Min Act: -0.1700
Data Index: 290295 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4898. Min Range: -7.4898
Max Act: 6.8023. Min Act: -0.1700
Data Index: 44098 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4898. Min Range: -7.4898
Max Act: 6.7710. Min Act: -0.1700
Data Index: 3848197 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19