Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2080 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4279. Min Range: -8.4279
Max Act: 8.4279. Min Act: -0.1700
Data Index: 2980997 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4279. Min Range: -8.4279
Max Act: 8.4279. Min Act: -0.1700
Data Index: 4746247 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4279. Min Range: -8.4279
Max Act: 8.0529. Min Act: -0.1700
Data Index: 7596487 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4279. Min Range: -8.4279
Max Act: 7.9904. Min Act: -0.1700
Data Index: 2867735 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4279. Min Range: -8.4279
Max Act: 7.8654. Min Act: -0.1700
Data Index: 3608353 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4279. Min Range: -8.4279
Max Act: 7.7404. Min Act: -0.1700
Data Index: 2824173 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4279. Min Range: -8.4279
Max Act: 7.8029. Min Act: -0.1700
Data Index: 2603002 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4279. Min Range: -8.4279
Max Act: 7.8029. Min Act: -0.1700
Data Index: 6189363 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4279. Min Range: -8.4279
Max Act: 7.7404. Min Act: -0.1700
Data Index: 7281187 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4279. Min Range: -8.4279
Max Act: 7.7404. Min Act: -0.1700
Data Index: 7412973 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4279. Min Range: -8.4279
Max Act: 7.7404. Min Act: -0.1700
Data Index: 886788 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4279. Min Range: -8.4279
Max Act: 7.7404. Min Act: -0.1700
Data Index: 195832 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4279. Min Range: -8.4279
Max Act: 7.6779. Min Act: -0.1700
Data Index: 5401467 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4279. Min Range: -8.4279
Max Act: 7.6779. Min Act: -0.1700
Data Index: 5094718 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4279. Min Range: -8.4279
Max Act: 7.6779. Min Act: -0.1700
Data Index: 2125044 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4279. Min Range: -8.4279
Max Act: 7.6154. Min Act: -0.1700
Data Index: 4095967 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4279. Min Range: -8.4279
Max Act: 7.5529. Min Act: -0.1700
Data Index: 4365733 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4279. Min Range: -8.4279
Max Act: 7.5529. Min Act: -0.1700
Data Index: 3741009 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4279. Min Range: -8.4279
Max Act: 7.5529. Min Act: -0.1700
Data Index: 1518032 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4279. Min Range: -8.4279
Max Act: 7.4904. Min Act: -0.1700
Data Index: 2145213 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19