Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3462. Min Range: -7.3462
Max Act: 7.3462. Min Act: -0.1700
Data Index: 1000090 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3462. Min Range: -7.3462
Max Act: 7.1899. Min Act: -0.1700
Data Index: 3495554 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3462. Min Range: -7.3462
Max Act: 7.0962. Min Act: -0.1700
Data Index: 5186074 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3462. Min Range: -7.3462
Max Act: 7.0337. Min Act: -0.1700
Data Index: 5098844 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3462. Min Range: -7.3462
Max Act: 6.8462. Min Act: -0.1700
Data Index: 1309790 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3462. Min Range: -7.3462
Max Act: 6.7837. Min Act: -0.1700
Data Index: 8128111 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3462. Min Range: -7.3462
Max Act: 6.8149. Min Act: -0.1700
Data Index: 5235591 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3462. Min Range: -7.3462
Max Act: 6.7524. Min Act: -0.1700
Data Index: 5956801 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3462. Min Range: -7.3462
Max Act: 6.7837. Min Act: -0.1700
Data Index: 4909563 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3462. Min Range: -7.3462
Max Act: 6.7837. Min Act: -0.1700
Data Index: 5333148 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3462. Min Range: -7.3462
Max Act: 6.7212. Min Act: -0.1700
Data Index: 1652744 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3462. Min Range: -7.3462
Max Act: 6.7212. Min Act: -0.1700
Data Index: 7915930 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3462. Min Range: -7.3462
Max Act: 6.7212. Min Act: -0.1700
Data Index: 1487705 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3462. Min Range: -7.3462
Max Act: 6.7212. Min Act: -0.1700
Data Index: 5167134 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3462. Min Range: -7.3462
Max Act: 6.6899. Min Act: -0.1700
Data Index: 5218435 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3462. Min Range: -7.3462
Max Act: 6.6899. Min Act: -0.1700
Data Index: 1433349 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3462. Min Range: -7.3462
Max Act: 6.6587. Min Act: -0.1700
Data Index: 2367880 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3462. Min Range: -7.3462
Max Act: 6.6587. Min Act: -0.1700
Data Index: 3325687 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3462. Min Range: -7.3462
Max Act: 6.6274. Min Act: -0.1700
Data Index: 7613975 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3462. Min Range: -7.3462
Max Act: 6.6899. Min Act: -0.1700
Data Index: 3339263 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19