Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3844 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5470. Min Range: -10.5470
Max Act: 10.5470. Min Act: -0.1700
Data Index: 1940795 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5470. Min Range: -10.5470
Max Act: 10.2345. Min Act: -0.1700
Data Index: 2222590 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5470. Min Range: -10.5470
Max Act: 10.2345. Min Act: -0.1700
Data Index: 4919335 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5470. Min Range: -10.5470
Max Act: 10.0470. Min Act: -0.1700
Data Index: 7295060 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5470. Min Range: -10.5470
Max Act: 9.9220. Min Act: -0.1700
Data Index: 704803 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5470. Min Range: -10.5470
Max Act: 9.7970. Min Act: -0.1700
Data Index: 2514560 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5470. Min Range: -10.5470
Max Act: 9.7970. Min Act: -0.1700
Data Index: 5446010 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5470. Min Range: -10.5470
Max Act: 9.6095. Min Act: -0.1700
Data Index: 1578990 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5470. Min Range: -10.5470
Max Act: 9.5470. Min Act: -0.1700
Data Index: 3396127 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5470. Min Range: -10.5470
Max Act: 9.6095. Min Act: -0.1700
Data Index: 5522491 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5470. Min Range: -10.5470
Max Act: 9.4845. Min Act: -0.1700
Data Index: 1094489 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5470. Min Range: -10.5470
Max Act: 9.3595. Min Act: -0.1700
Data Index: 5148266 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5470. Min Range: -10.5470
Max Act: 9.3595. Min Act: -0.1700
Data Index: 4711298 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5470. Min Range: -10.5470
Max Act: 9.4220. Min Act: -0.1700
Data Index: 5415682 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5470. Min Range: -10.5470
Max Act: 9.3595. Min Act: -0.1700
Data Index: 1216235 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5470. Min Range: -10.5470
Max Act: 9.2970. Min Act: -0.1700
Data Index: 6154535 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5470. Min Range: -10.5470
Max Act: 9.2970. Min Act: -0.1700
Data Index: 5936071 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5470. Min Range: -10.5470
Max Act: 9.2345. Min Act: -0.1700
Data Index: 722592 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5470. Min Range: -10.5470
Max Act: 9.1720. Min Act: -0.1700
Data Index: 3712008 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5470. Min Range: -10.5470
Max Act: 9.2345. Min Act: -0.1700
Data Index: 2952701 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19