Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3985 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.4032. Min Act: -0.1700
Data Index: 5119406 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.3407. Min Act: -0.1700
Data Index: 5511023 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.3407. Min Act: -0.1700
Data Index: 360688 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.3094. Min Act: -0.1700
Data Index: 5304836 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.2782. Min Act: -0.1700
Data Index: 853229 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.2469. Min Act: -0.1700
Data Index: 4223217 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.2157. Min Act: -0.1700
Data Index: 3922190 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.2782. Min Act: -0.1700
Data Index: 3078008 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.2157. Min Act: -0.1700
Data Index: 4460461 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.1219. Min Act: -0.1700
Data Index: 1534616 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.2469. Min Act: -0.1700
Data Index: 6473835 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.2157. Min Act: -0.1700
Data Index: 3930273 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.1844. Min Act: -0.1700
Data Index: 390781 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.1844. Min Act: -0.1700
Data Index: 1522180 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.1219. Min Act: -0.1700
Data Index: 6473829 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.1219. Min Act: -0.1700
Data Index: 3421554 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.1532. Min Act: -0.1700
Data Index: 7514233 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.0907. Min Act: -0.1700
Data Index: 4299614 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.1219. Min Act: -0.1700
Data Index: 2501200 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4032. Min Range: -5.4032
Max Act: 5.0594. Min Act: -0.1700
Data Index: 1078828 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19