Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4000 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.4817. Min Act: -0.1700
Data Index: 2101864 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.4817. Min Act: -0.1700
Data Index: 3060413 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.4504. Min Act: -0.1700
Data Index: 878526 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.4192. Min Act: -0.1700
Data Index: 5494401 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.4504. Min Act: -0.1700
Data Index: 4806107 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3879. Min Act: -0.1700
Data Index: 6889648 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3567. Min Act: -0.1700
Data Index: 1935249 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3567. Min Act: -0.1700
Data Index: 589291 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3567. Min Act: -0.1700
Data Index: 3405354 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.2942. Min Act: -0.1700
Data Index: 4688121 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3254. Min Act: -0.1700
Data Index: 5792641 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3254. Min Act: -0.1700
Data Index: 2728552 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3254. Min Act: -0.1700
Data Index: 6784828 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.3254. Min Act: -0.1700
Data Index: 7878949 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.2942. Min Act: -0.1700
Data Index: 5667649 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.2629. Min Act: -0.1700
Data Index: 1666720 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.2942. Min Act: -0.1700
Data Index: 2338440 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.2942. Min Act: -0.1700
Data Index: 3551209 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.2942. Min Act: -0.1700
Data Index: 3531101 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4817. Min Range: -4.4817
Max Act: 4.2942. Min Act: -0.1700
Data Index: 6349751 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19