Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3079 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4012. Min Range: -8.4012
Max Act: 8.4012. Min Act: -0.1700
Data Index: 6404971 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4012. Min Range: -8.4012
Max Act: 8.2762. Min Act: -0.1700
Data Index: 4372143 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4012. Min Range: -8.4012
Max Act: 8.2762. Min Act: -0.1700
Data Index: 3824541 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4012. Min Range: -8.4012
Max Act: 8.1512. Min Act: -0.1700
Data Index: 3510122 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4012. Min Range: -8.4012
Max Act: 8.0887. Min Act: -0.1700
Data Index: 2295478 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4012. Min Range: -8.4012
Max Act: 8.0262. Min Act: -0.1700
Data Index: 5917411 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4012. Min Range: -8.4012
Max Act: 8.0262. Min Act: -0.1700
Data Index: 964616 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4012. Min Range: -8.4012
Max Act: 8.0262. Min Act: -0.1700
Data Index: 3922794 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4012. Min Range: -8.4012
Max Act: 7.9637. Min Act: -0.1700
Data Index: 5627362 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4012. Min Range: -8.4012
Max Act: 7.9637. Min Act: -0.1700
Data Index: 4613430 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4012. Min Range: -8.4012
Max Act: 7.9637. Min Act: -0.1700
Data Index: 552048 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4012. Min Range: -8.4012
Max Act: 7.9637. Min Act: -0.1700
Data Index: 1689465 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4012. Min Range: -8.4012
Max Act: 7.9637. Min Act: -0.1700
Data Index: 5286114 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4012. Min Range: -8.4012
Max Act: 7.9012. Min Act: -0.1700
Data Index: 7092530 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4012. Min Range: -8.4012
Max Act: 7.9012. Min Act: -0.1700
Data Index: 5734684 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4012. Min Range: -8.4012
Max Act: 7.9012. Min Act: -0.1700
Data Index: 1484126 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4012. Min Range: -8.4012
Max Act: 7.8387. Min Act: -0.1700
Data Index: 2840232 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4012. Min Range: -8.4012
Max Act: 7.9012. Min Act: -0.1700
Data Index: 1285128 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4012. Min Range: -8.4012
Max Act: 7.9012. Min Act: -0.1700
Data Index: 8259007 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4012. Min Range: -8.4012
Max Act: 7.8387. Min Act: -0.1700
Data Index: 757859 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19