Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 450 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2355. Min Range: -6.2355
Max Act: 6.2355. Min Act: -0.1700
Data Index: 6273618 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2355. Min Range: -6.2355
Max Act: 6.1730. Min Act: -0.1700
Data Index: 7943309 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2355. Min Range: -6.2355
Max Act: 6.1105. Min Act: -0.1700
Data Index: 6128530 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2355. Min Range: -6.2355
Max Act: 6.1418. Min Act: -0.1700
Data Index: 310675 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2355. Min Range: -6.2355
Max Act: 6.1105. Min Act: -0.1700
Data Index: 8577156 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2355. Min Range: -6.2355
Max Act: 6.0793. Min Act: -0.1700
Data Index: 3943803 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2355. Min Range: -6.2355
Max Act: 6.0793. Min Act: -0.1700
Data Index: 111428 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2355. Min Range: -6.2355
Max Act: 6.0793. Min Act: -0.1700
Data Index: 8775393 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2355. Min Range: -6.2355
Max Act: 5.9855. Min Act: -0.1700
Data Index: 8068415 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2355. Min Range: -6.2355
Max Act: 5.9855. Min Act: -0.1700
Data Index: 5441031 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2355. Min Range: -6.2355
Max Act: 5.9543. Min Act: -0.1700
Data Index: 5875368 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2355. Min Range: -6.2355
Max Act: 5.9230. Min Act: -0.1700
Data Index: 7088163 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2355. Min Range: -6.2355
Max Act: 5.9230. Min Act: -0.1700
Data Index: 716859 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2355. Min Range: -6.2355
Max Act: 5.8918. Min Act: -0.1700
Data Index: 3214865 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2355. Min Range: -6.2355
Max Act: 5.8605. Min Act: -0.1700
Data Index: 7008976 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2355. Min Range: -6.2355
Max Act: 5.8918. Min Act: -0.1700
Data Index: 3892176 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2355. Min Range: -6.2355
Max Act: 5.8605. Min Act: -0.1700
Data Index: 4345823 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2355. Min Range: -6.2355
Max Act: 5.8605. Min Act: -0.1700
Data Index: 7322624 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2355. Min Range: -6.2355
Max Act: 5.8293. Min Act: -0.1700
Data Index: 4941964 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2355. Min Range: -6.2355
Max Act: 5.8605. Min Act: -0.1700
Data Index: 1529858 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19