Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2930 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.3669. Min Act: -0.1700
Data Index: 7570287 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.3044. Min Act: -0.1700
Data Index: 4860251 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.2419. Min Act: -0.1700
Data Index: 906093 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.2419. Min Act: -0.1700
Data Index: 418353 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.2419. Min Act: -0.1700
Data Index: 7132350 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.1169. Min Act: -0.1700
Data Index: 3013500 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.1794. Min Act: -0.1700
Data Index: 6549152 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.1169. Min Act: -0.1700
Data Index: 4646935 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.1169. Min Act: -0.1700
Data Index: 6789654 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.1169. Min Act: -0.1700
Data Index: 463345 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.1169. Min Act: -0.1700
Data Index: 827049 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.0544. Min Act: -0.1700
Data Index: 5438601 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.0544. Min Act: -0.1700
Data Index: 1626397 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.0544. Min Act: -0.1700
Data Index: 3577136 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.0544. Min Act: -0.1700
Data Index: 1734273 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.0544. Min Act: -0.1700
Data Index: 262192 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.0544. Min Act: -0.1700
Data Index: 5958185 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.0544. Min Act: -0.1700
Data Index: 8441317 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3669. Min Range: -9.3669
Max Act: 9.0544. Min Act: -0.1700
Data Index: 3651926 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3669. Min Range: -9.3669
Max Act: 8.9919. Min Act: -0.1700
Data Index: 643147 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19