Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1789 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0638. Min Range: -6.0638
Max Act: 6.0638. Min Act: -0.1700
Data Index: 1796392 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.9700. Min Act: -0.1700
Data Index: 1154125 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.9700. Min Act: -0.1700
Data Index: 1623288 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.8763. Min Act: -0.1700
Data Index: 6263837 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.8450. Min Act: -0.1700
Data Index: 6983274 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.7825. Min Act: -0.1700
Data Index: 7700304 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.7513. Min Act: -0.1700
Data Index: 8633174 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.7513. Min Act: -0.1700
Data Index: 4090770 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.7200. Min Act: -0.1700
Data Index: 8270075 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.7200. Min Act: -0.1700
Data Index: 6278096 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.7200. Min Act: -0.1700
Data Index: 6448617 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.6575. Min Act: -0.1700
Data Index: 5229495 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.6575. Min Act: -0.1700
Data Index: 6151055 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.6263. Min Act: -0.1700
Data Index: 5188036 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.6575. Min Act: -0.1700
Data Index: 4392258 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.6575. Min Act: -0.1700
Data Index: 4345524 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.6575. Min Act: -0.1700
Data Index: 8197239 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.6263. Min Act: -0.1700
Data Index: 2680098 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.6263. Min Act: -0.1700
Data Index: 5180720 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0638. Min Range: -6.0638
Max Act: 5.6263. Min Act: -0.1700
Data Index: 534399 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19