Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3392 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.6112. Min Act: -0.1700
Data Index: 8741507 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.5487. Min Act: -0.1700
Data Index: 6562456 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.3612. Min Act: -0.1700
Data Index: 3727663 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.3612. Min Act: -0.1700
Data Index: 3049306 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.3925. Min Act: -0.1700
Data Index: 7963176 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.3300. Min Act: -0.1700
Data Index: 7251582 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.3300. Min Act: -0.1700
Data Index: 5181903 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.2987. Min Act: -0.1700
Data Index: 8231790 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.2362. Min Act: -0.1700
Data Index: 3198698 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.2050. Min Act: -0.1700
Data Index: 1211459 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.2050. Min Act: -0.1700
Data Index: 6924153 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.2362. Min Act: -0.1700
Data Index: 124098 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.2050. Min Act: -0.1700
Data Index: 235396 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.1737. Min Act: -0.1700
Data Index: 3090103 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.2050. Min Act: -0.1700
Data Index: 355209 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.1425. Min Act: -0.1700
Data Index: 5444707 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.1425. Min Act: -0.1700
Data Index: 4163124 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.1425. Min Act: -0.1700
Data Index: 2950643 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.1112. Min Act: -0.1700
Data Index: 1928022 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6112. Min Range: -7.6112
Max Act: 7.0800. Min Act: -0.1700
Data Index: 5307505 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19