Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 627 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0241. Min Range: -7.0241
Max Act: 7.0241. Min Act: -0.1700
Data Index: 2705141 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0241. Min Range: -7.0241
Max Act: 7.0241. Min Act: -0.1700
Data Index: 3886664 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.9929. Min Act: -0.1700
Data Index: 944378 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.9616. Min Act: -0.1700
Data Index: 7269649 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.9616. Min Act: -0.1700
Data Index: 7982817 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.9616. Min Act: -0.1700
Data Index: 1337289 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.8991. Min Act: -0.1700
Data Index: 2967593 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.8991. Min Act: -0.1700
Data Index: 5874081 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.8991. Min Act: -0.1700
Data Index: 4707980 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.8679. Min Act: -0.1700
Data Index: 2656105 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.8366. Min Act: -0.1700
Data Index: 5956360 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.8366. Min Act: -0.1700
Data Index: 1731276 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.7741. Min Act: -0.1700
Data Index: 6466995 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.7741. Min Act: -0.1700
Data Index: 4892910 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.7429. Min Act: -0.1700
Data Index: 4446706 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.7429. Min Act: -0.1700
Data Index: 8006750 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.7429. Min Act: -0.1700
Data Index: 6283302 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.7116. Min Act: -0.1700
Data Index: 3845876 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.7429. Min Act: -0.1700
Data Index: 2743257 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0241. Min Range: -7.0241
Max Act: 6.7116. Min Act: -0.1700
Data Index: 2360701 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19