Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 736 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.7080. Min Act: -0.1700
Data Index: 832114 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.6455. Min Act: -0.1700
Data Index: 621280 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.3643. Min Act: -0.1700
Data Index: 3717778 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.3018. Min Act: -0.1700
Data Index: 2918804 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.2080. Min Act: -0.1700
Data Index: 3905167 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.2080. Min Act: -0.1700
Data Index: 3138647 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.2080. Min Act: -0.1700
Data Index: 6515091 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.2393. Min Act: -0.1700
Data Index: 966491 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.2080. Min Act: -0.1700
Data Index: 3458770 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.2080. Min Act: -0.1700
Data Index: 1046216 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.1455. Min Act: -0.1700
Data Index: 4174677 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.1455. Min Act: -0.1700
Data Index: 249894 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.1143. Min Act: -0.1700
Data Index: 606101 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.1143. Min Act: -0.1700
Data Index: 6970077 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.1143. Min Act: -0.1700
Data Index: 3913940 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.1143. Min Act: -0.1700
Data Index: 5493180 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.0830. Min Act: -0.1700
Data Index: 2304647 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.0518. Min Act: -0.1700
Data Index: 2322037 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.0518. Min Act: -0.1700
Data Index: 189637 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7080. Min Range: -6.7080
Max Act: 6.0518. Min Act: -0.1700
Data Index: 4162167 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19