Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1638 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.4580. Min Act: -0.1700
Data Index: 1013939 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.3955. Min Act: -0.1700
Data Index: 8648457 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.2705. Min Act: -0.1700
Data Index: 7782739 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.2705. Min Act: -0.1700
Data Index: 3922617 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.2705. Min Act: -0.1700
Data Index: 7554818 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.2080. Min Act: -0.1700
Data Index: 3928797 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.1455. Min Act: -0.1700
Data Index: 4733421 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.1455. Min Act: -0.1700
Data Index: 718053 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.1455. Min Act: -0.1700
Data Index: 4663102 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.1455. Min Act: -0.1700
Data Index: 7577973 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.1455. Min Act: -0.1700
Data Index: 7049291 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.1455. Min Act: -0.1700
Data Index: 1132090 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.0830. Min Act: -0.1700
Data Index: 712930 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.0830. Min Act: -0.1700
Data Index: 4408513 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.0830. Min Act: -0.1700
Data Index: 7875684 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.0830. Min Act: -0.1700
Data Index: 1625375 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.0830. Min Act: -0.1700
Data Index: 4637469 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.0205. Min Act: -0.1700
Data Index: 3540181 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.0205. Min Act: -0.1700
Data Index: 2209186 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4580. Min Range: -10.4580
Max Act: 10.0205. Min Act: -0.1700
Data Index: 2423149 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19