Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4700. Min Range: -7.4700
Max Act: 7.4700. Min Act: -0.1700
Data Index: 779931 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4700. Min Range: -7.4700
Max Act: 7.0950. Min Act: -0.1700
Data Index: 4433153 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4700. Min Range: -7.4700
Max Act: 7.0950. Min Act: -0.1700
Data Index: 4173619 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4700. Min Range: -7.4700
Max Act: 6.9700. Min Act: -0.1700
Data Index: 2427696 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4700. Min Range: -7.4700
Max Act: 6.9075. Min Act: -0.1696
Data Index: 7866468 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4700. Min Range: -7.4700
Max Act: 6.8763. Min Act: -0.1700
Data Index: 6600810 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4700. Min Range: -7.4700
Max Act: 6.8763. Min Act: -0.1700
Data Index: 830538 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4700. Min Range: -7.4700
Max Act: 6.8138. Min Act: -0.1700
Data Index: 6577049 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4700. Min Range: -7.4700
Max Act: 6.7513. Min Act: -0.1700
Data Index: 6138632 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4700. Min Range: -7.4700
Max Act: 6.7200. Min Act: -0.1700
Data Index: 4008876 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4700. Min Range: -7.4700
Max Act: 6.6888. Min Act: -0.1700
Data Index: 7242956 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4700. Min Range: -7.4700
Max Act: 6.6888. Min Act: -0.1700
Data Index: 3858323 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4700. Min Range: -7.4700
Max Act: 6.6575. Min Act: -0.1700
Data Index: 2342530 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4700. Min Range: -7.4700
Max Act: 6.6888. Min Act: -0.1700
Data Index: 3947527 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4700. Min Range: -7.4700
Max Act: 6.6575. Min Act: -0.1700
Data Index: 4432039 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4700. Min Range: -7.4700
Max Act: 6.6263. Min Act: -0.1700
Data Index: 3839386 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4700. Min Range: -7.4700
Max Act: 6.6263. Min Act: -0.1700
Data Index: 732483 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4700. Min Range: -7.4700
Max Act: 6.6263. Min Act: -0.1700
Data Index: 1962212 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4700. Min Range: -7.4700
Max Act: 6.6263. Min Act: -0.1700
Data Index: 3445314 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4700. Min Range: -7.4700
Max Act: 6.6263. Min Act: -0.1700
Data Index: 958806 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19