Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1612 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.6619. Min Act: -0.1700
Data Index: 40305 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.6307. Min Act: -0.1700
Data Index: 1942504 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.5682. Min Act: -0.1700
Data Index: 6843480 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.5369. Min Act: -0.1700
Data Index: 2398509 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.5682. Min Act: -0.1700
Data Index: 5595300 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.5057. Min Act: -0.1700
Data Index: 2112091 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.4119. Min Act: -0.1700
Data Index: 3637188 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.2869. Min Act: -0.1700
Data Index: 5649370 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.2869. Min Act: -0.1700
Data Index: 653720 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.2557. Min Act: -0.1700
Data Index: 964966 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.2557. Min Act: -0.1700
Data Index: 5519773 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.2557. Min Act: -0.1700
Data Index: 2220102 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.2557. Min Act: -0.1700
Data Index: 7029654 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.1932. Min Act: -0.1700
Data Index: 7935194 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.2244. Min Act: -0.1700
Data Index: 7570546 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.1619. Min Act: -0.1700
Data Index: 8441894 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.1619. Min Act: -0.1700
Data Index: 6631225 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.1619. Min Act: -0.1700
Data Index: 2422604 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.1307. Min Act: -0.1700
Data Index: 8799571 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6619. Min Range: -6.6619
Max Act: 6.0994. Min Act: -0.1700
Data Index: 3736695 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19