Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5570 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.9127. Min Act: -0.1700
Data Index: 1185224 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.7877. Min Act: -0.1700
Data Index: 1768503 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.7877. Min Act: -0.1700
Data Index: 5671672 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.6627. Min Act: -0.1700
Data Index: 2228821 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.6627. Min Act: -0.1700
Data Index: 802714 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.5689. Min Act: -0.1700
Data Index: 3049150 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.5689. Min Act: -0.1700
Data Index: 6454684 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.5064. Min Act: -0.1700
Data Index: 104061 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.5377. Min Act: -0.1700
Data Index: 5026274 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.5064. Min Act: -0.1700
Data Index: 5892747 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.5064. Min Act: -0.1700
Data Index: 4035179 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.4752. Min Act: -0.1700
Data Index: 2505481 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.4439. Min Act: -0.1700
Data Index: 7233826 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.4439. Min Act: -0.1700
Data Index: 2352022 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.4439. Min Act: -0.1700
Data Index: 3540922 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.4752. Min Act: -0.1700
Data Index: 5281223 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.3814. Min Act: -0.1700
Data Index: 7838084 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.3814. Min Act: -0.1700
Data Index: 7787581 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.3814. Min Act: -0.1700
Data Index: 2770332 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9127. Min Range: -7.9127
Max Act: 7.3189. Min Act: -0.1700
Data Index: 5374137 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19