Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4912 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.8939. Min Act: -0.1700
Data Index: 4605737 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.8314. Min Act: -0.1700
Data Index: 7475189 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.8939. Min Act: -0.1700
Data Index: 6961508 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.8939. Min Act: -0.1700
Data Index: 6568926 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.7689. Min Act: -0.1700
Data Index: 6961507 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.7689. Min Act: -0.1700
Data Index: 1551197 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.6439. Min Act: -0.1700
Data Index: 6748565 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.5814. Min Act: -0.1700
Data Index: 2296507 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.5814. Min Act: -0.1700
Data Index: 128388 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.5189. Min Act: -0.1700
Data Index: 6340244 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.5189. Min Act: -0.1700
Data Index: 5383557 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.5189. Min Act: -0.1695
Data Index: 3069794 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.4564. Min Act: -0.1700
Data Index: 1622290 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.3939. Min Act: -0.1700
Data Index: 2676244 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.3626. Min Act: -0.1700
Data Index: 1196221 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.3314. Min Act: -0.1700
Data Index: 8021092 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.3314. Min Act: -0.1700
Data Index: 1094254 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.3314. Min Act: -0.1700
Data Index: 6510237 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.3001. Min Act: -0.1700
Data Index: 61844 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8939. Min Range: -8.8939
Max Act: 8.2689. Min Act: -0.1700
Data Index: 7620070 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19