Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 725 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.3809. Min Act: -0.1700
Data Index: 7671188 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.3184. Min Act: -0.1700
Data Index: 1217754 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.2871. Min Act: -0.1700
Data Index: 638444 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.2246. Min Act: -0.1700
Data Index: 5405239 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.2246. Min Act: -0.1700
Data Index: 692421 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.2246. Min Act: -0.1700
Data Index: 8800391 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.1621. Min Act: -0.1700
Data Index: 4875950 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.1934. Min Act: -0.1700
Data Index: 5280749 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.1934. Min Act: -0.1700
Data Index: 1975659 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.1621. Min Act: -0.1700
Data Index: 5019575 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.1934. Min Act: -0.1700
Data Index: 3074093 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.1621. Min Act: -0.1700
Data Index: 8633297 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.1309. Min Act: -0.1700
Data Index: 4311201 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.0996. Min Act: -0.1700
Data Index: 2031944 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.0996. Min Act: -0.1700
Data Index: 6931049 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.0996. Min Act: -0.1700
Data Index: 2284209 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.0996. Min Act: -0.1700
Data Index: 3867954 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.0996. Min Act: -0.1700
Data Index: 2332218 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.0996. Min Act: -0.1700
Data Index: 7358000 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3809. Min Range: -5.3809
Max Act: 5.0996. Min Act: -0.1700
Data Index: 882528 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19