Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2878 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.8385. Min Act: -0.1700
Data Index: 5986759 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.6510. Min Act: -0.1700
Data Index: 6780816 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.6510. Min Act: -0.1700
Data Index: 1574651 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.5885. Min Act: -0.1700
Data Index: 7956846 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.5572. Min Act: -0.1700
Data Index: 977754 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.4947. Min Act: -0.1700
Data Index: 1426094 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.4947. Min Act: -0.1700
Data Index: 8038493 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.4947. Min Act: -0.1700
Data Index: 850064 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.4635. Min Act: -0.1700
Data Index: 3884608 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.4322. Min Act: -0.1700
Data Index: 7620931 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.4322. Min Act: -0.1700
Data Index: 6002256 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.4322. Min Act: -0.1700
Data Index: 686321 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.4322. Min Act: -0.1700
Data Index: 1897062 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.4322. Min Act: -0.1700
Data Index: 2556119 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.4322. Min Act: -0.1700
Data Index: 7174752 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.4010. Min Act: -0.1700
Data Index: 3684029 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.3385. Min Act: -0.1700
Data Index: 4824086 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.3385. Min Act: -0.1700
Data Index: 3841605 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.3697. Min Act: -0.1700
Data Index: 3951118 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8385. Min Range: -4.8385
Max Act: 4.3385. Min Act: -0.1700
Data Index: 4914175 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19