Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1027 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0255. Min Range: -4.0255
Max Act: 4.0255. Min Act: -0.1700
Data Index: 3913413 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0255. Min Range: -4.0255
Max Act: 4.0255. Min Act: -0.1700
Data Index: 7416481 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.9942. Min Act: -0.1700
Data Index: 3362507 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.9942. Min Act: -0.1700
Data Index: 545785 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.9317. Min Act: -0.1700
Data Index: 5251756 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.9317. Min Act: -0.1700
Data Index: 3109360 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.8692. Min Act: -0.1700
Data Index: 3490465 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.8692. Min Act: -0.1700
Data Index: 7513852 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.8692. Min Act: -0.1700
Data Index: 8428996 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.8379. Min Act: -0.1700
Data Index: 7564588 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.8692. Min Act: -0.1700
Data Index: 306874 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.8692. Min Act: -0.1700
Data Index: 3788079 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.8379. Min Act: -0.1700
Data Index: 5438252 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.8066. Min Act: -0.1700
Data Index: 2303658 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.8379. Min Act: -0.1700
Data Index: 3051712 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.8379. Min Act: -0.1700
Data Index: 6540947 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.8379. Min Act: -0.1700
Data Index: 7478122 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.8379. Min Act: -0.1700
Data Index: 5104191 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.8379. Min Act: -0.1700
Data Index: 5742236 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0255. Min Range: -4.0255
Max Act: 3.8066. Min Act: -0.1700
Data Index: 5435419 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19