Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3139 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2330. Min Range: -6.2330
Max Act: 6.2330. Min Act: -0.1700
Data Index: 1736998 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2330. Min Range: -6.2330
Max Act: 6.2017. Min Act: -0.1700
Data Index: 4054094 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2330. Min Range: -6.2330
Max Act: 6.1080. Min Act: -0.1700
Data Index: 2636441 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2330. Min Range: -6.2330
Max Act: 6.0767. Min Act: -0.1700
Data Index: 1765899 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2330. Min Range: -6.2330
Max Act: 6.0455. Min Act: -0.1700
Data Index: 7496958 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2330. Min Range: -6.2330
Max Act: 6.0142. Min Act: -0.1700
Data Index: 6817793 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2330. Min Range: -6.2330
Max Act: 5.9830. Min Act: -0.1700
Data Index: 1448533 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2330. Min Range: -6.2330
Max Act: 5.9517. Min Act: -0.1700
Data Index: 4593835 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2330. Min Range: -6.2330
Max Act: 5.9517. Min Act: -0.1700
Data Index: 4600295 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2330. Min Range: -6.2330
Max Act: 5.9205. Min Act: -0.1700
Data Index: 1621872 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2330. Min Range: -6.2330
Max Act: 5.8580. Min Act: -0.1700
Data Index: 5489126 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2330. Min Range: -6.2330
Max Act: 5.8892. Min Act: -0.1700
Data Index: 2807681 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2330. Min Range: -6.2330
Max Act: 5.8892. Min Act: -0.1700
Data Index: 461255 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2330. Min Range: -6.2330
Max Act: 5.8580. Min Act: -0.1700
Data Index: 1595599 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2330. Min Range: -6.2330
Max Act: 5.8580. Min Act: -0.1700
Data Index: 7748817 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2330. Min Range: -6.2330
Max Act: 5.8580. Min Act: -0.1700
Data Index: 218930 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2330. Min Range: -6.2330
Max Act: 5.8267. Min Act: -0.1700
Data Index: 1436635 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2330. Min Range: -6.2330
Max Act: 5.8267. Min Act: -0.1700
Data Index: 1794092 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2330. Min Range: -6.2330
Max Act: 5.8267. Min Act: -0.1700
Data Index: 1200100 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2330. Min Range: -6.2330
Max Act: 5.7955. Min Act: -0.1700
Data Index: 5320068 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19