Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3234 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.4778. Min Act: -0.1700
Data Index: 8515065 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.3053. Min Act: -0.1700
Data Index: 38343 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.2425. Min Act: -0.1700
Data Index: 6864651 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.2267. Min Act: -0.1700
Data Index: 713354 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.1953. Min Act: -0.1700
Data Index: 6784549 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.1796. Min Act: -0.1700
Data Index: 557445 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.1796. Min Act: -0.1700
Data Index: 1972257 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.1638. Min Act: -0.1700
Data Index: 7686240 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.1638. Min Act: -0.1700
Data Index: 2267912 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.1481. Min Act: -0.1700
Data Index: 6801916 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.1481. Min Act: -0.1700
Data Index: 84143 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.1481. Min Act: -0.1700
Data Index: 4794419 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.1324. Min Act: -0.1700
Data Index: 1670898 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.1008. Min Act: -0.1700
Data Index: 3726799 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.1008. Min Act: -0.1700
Data Index: 3822195 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.1008. Min Act: -0.1700
Data Index: 8541158 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.0851. Min Act: -0.1700
Data Index: 8738099 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.0693. Min Act: -0.1700
Data Index: 6312900 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.0851. Min Act: -0.1700
Data Index: 2002430 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4778. Min Range: -3.4778
Max Act: 3.0693. Min Act: -0.1700
Data Index: 6317393 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19