Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2695 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0540. Min Range: -6.0540
Max Act: 6.0540. Min Act: -0.1700
Data Index: 4930256 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.8978. Min Act: -0.1700
Data Index: 5490718 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.8353. Min Act: -0.1700
Data Index: 8213682 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.8353. Min Act: -0.1700
Data Index: 6536049 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.7728. Min Act: -0.1700
Data Index: 5674352 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.7415. Min Act: -0.1700
Data Index: 2859180 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.7415. Min Act: -0.1700
Data Index: 1529363 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.7103. Min Act: -0.1700
Data Index: 2232176 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.6790. Min Act: -0.1700
Data Index: 4411196 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.6790. Min Act: -0.1700
Data Index: 382613 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.6790. Min Act: -0.1700
Data Index: 7855081 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.6790. Min Act: -0.1700
Data Index: 8695133 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.5853. Min Act: -0.1700
Data Index: 6727438 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.5853. Min Act: -0.1700
Data Index: 4695984 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.5853. Min Act: -0.1700
Data Index: 6831113 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.5540. Min Act: -0.1700
Data Index: 2076051 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.5540. Min Act: -0.1700
Data Index: 4272299 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.5540. Min Act: -0.1700
Data Index: 2727423 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.5228. Min Act: -0.1700
Data Index: 3551723 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0540. Min Range: -6.0540
Max Act: 5.5853. Min Act: -0.1700
Data Index: 7285042 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19