Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1295 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.6552. Min Act: -0.1700
Data Index: 4028638 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.5927. Min Act: -0.1700
Data Index: 4489949 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.4052. Min Act: -0.1700
Data Index: 2043944 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.3739. Min Act: -0.1700
Data Index: 2060328 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.3427. Min Act: -0.1700
Data Index: 6190896 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.3114. Min Act: -0.1700
Data Index: 8331755 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.2489. Min Act: -0.1700
Data Index: 2198626 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.2802. Min Act: -0.1700
Data Index: 6823021 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.2802. Min Act: -0.1700
Data Index: 8718501 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.2489. Min Act: -0.1700
Data Index: 4388983 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.2489. Min Act: -0.1700
Data Index: 7943576 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.2802. Min Act: -0.1700
Data Index: 3266089 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.2177. Min Act: -0.1700
Data Index: 5973306 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.2177. Min Act: -0.1700
Data Index: 7258540 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.2177. Min Act: -0.1700
Data Index: 2995172 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.2177. Min Act: -0.1700
Data Index: 4606171 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.1864. Min Act: -0.1700
Data Index: 3500773 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.1864. Min Act: -0.1700
Data Index: 7162319 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.1864. Min Act: -0.1700
Data Index: 6835111 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6552. Min Range: -5.6552
Max Act: 5.1552. Min Act: -0.1700
Data Index: 135364 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19