Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5147 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.7249. Min Act: -0.1700
Data Index: 2677395 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.3499. Min Act: -0.1700
Data Index: 5174797 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.2562. Min Act: -0.1700
Data Index: 5165211 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.2874. Min Act: -0.1700
Data Index: 4057684 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.1937. Min Act: -0.1700
Data Index: 2854985 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.2249. Min Act: -0.1700
Data Index: 196524 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.2249. Min Act: -0.1700
Data Index: 6648365 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.2249. Min Act: -0.1700
Data Index: 6161031 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.1937. Min Act: -0.1700
Data Index: 2566363 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.1937. Min Act: -0.1700
Data Index: 710837 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.1312. Min Act: -0.1700
Data Index: 4433946 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.1624. Min Act: -0.1700
Data Index: 5780152 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.1312. Min Act: -0.1700
Data Index: 6680785 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.1624. Min Act: -0.1700
Data Index: 4092292 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.1624. Min Act: -0.1700
Data Index: 2106068 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.0999. Min Act: -0.1700
Data Index: 728146 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.0999. Min Act: -0.1700
Data Index: 1698872 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.0687. Min Act: -0.1700
Data Index: 3164990 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.0687. Min Act: -0.1700
Data Index: 3978414 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7249. Min Range: -6.7249
Max Act: 6.0374. Min Act: -0.1700
Data Index: 7171466 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19