Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5457 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.4646. Min Act: -0.1700
Data Index: 459428 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.4021. Min Act: -0.1700
Data Index: 3766533 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.3708. Min Act: -0.1700
Data Index: 459425 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.3708. Min Act: -0.1700
Data Index: 1170194 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.3396. Min Act: -0.1700
Data Index: 7961308 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.3396. Min Act: -0.1700
Data Index: 3766534 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.3083. Min Act: -0.1700
Data Index: 4700032 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.3083. Min Act: -0.1700
Data Index: 4717174 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.2771. Min Act: -0.1700
Data Index: 5923016 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.2771. Min Act: -0.1700
Data Index: 2820318 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.2771. Min Act: -0.1700
Data Index: 2575412 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.2458. Min Act: -0.1700
Data Index: 4084844 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.2146. Min Act: -0.1700
Data Index: 6031068 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.2458. Min Act: -0.1700
Data Index: 5726231 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.2146. Min Act: -0.1700
Data Index: 1337738 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.1833. Min Act: -0.1700
Data Index: 8797156 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.1833. Min Act: -0.1700
Data Index: 3039483 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.1833. Min Act: -0.1700
Data Index: 2859606 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.1521. Min Act: -0.1700
Data Index: 4700033 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4646. Min Range: -4.4646
Max Act: 4.1833. Min Act: -0.1700
Data Index: 2881937 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19