Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.9001. Min Act: -0.1700
Data Index: 134023 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.8064. Min Act: -0.1700
Data Index: 262761 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.7439. Min Act: -0.1700
Data Index: 5027869 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.7126. Min Act: -0.1700
Data Index: 4808599 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.7126. Min Act: -0.1700
Data Index: 3343689 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.6814. Min Act: -0.1700
Data Index: 8137566 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.6501. Min Act: -0.1700
Data Index: 5591019 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.6501. Min Act: -0.1700
Data Index: 869382 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.5876. Min Act: -0.1700
Data Index: 730629 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.6189. Min Act: -0.1700
Data Index: 2591980 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.5564. Min Act: -0.1700
Data Index: 3457998 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.5876. Min Act: -0.1700
Data Index: 5562421 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.5564. Min Act: -0.1700
Data Index: 4950462 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.5251. Min Act: -0.1700
Data Index: 2113319 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.4939. Min Act: -0.1700
Data Index: 7886113 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.4939. Min Act: -0.1700
Data Index: 6365147 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.4626. Min Act: -0.1700
Data Index: 7430671 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.4626. Min Act: -0.1700
Data Index: 1274725 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.4626. Min Act: -0.1700
Data Index: 478544 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9001. Min Range: -6.9001
Max Act: 6.4939. Min Act: -0.1700
Data Index: 6935201 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19