Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3608 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3950. Min Range: -7.3950
Max Act: 7.3950. Min Act: -0.1700
Data Index: 660035 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.9888. Min Act: -0.1700
Data Index: 4623368 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.9263. Min Act: -0.1700
Data Index: 767204 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.9263. Min Act: -0.1700
Data Index: 609153 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.8950. Min Act: -0.1700
Data Index: 1053937 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.8325. Min Act: -0.1700
Data Index: 4492024 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.8325. Min Act: -0.1700
Data Index: 4131881 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.8325. Min Act: -0.1700
Data Index: 291980 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.8013. Min Act: -0.1700
Data Index: 8376250 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.8013. Min Act: -0.1700
Data Index: 5951604 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.7700. Min Act: -0.1700
Data Index: 3037001 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.7700. Min Act: -0.1700
Data Index: 1337308 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.7388. Min Act: -0.1700
Data Index: 2596780 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.7388. Min Act: -0.1700
Data Index: 1341450 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.6763. Min Act: -0.1700
Data Index: 3847194 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.6763. Min Act: -0.1700
Data Index: 7936919 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.7075. Min Act: -0.1700
Data Index: 2294919 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.6763. Min Act: -0.1700
Data Index: 5723505 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.6763. Min Act: -0.1700
Data Index: 1738351 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3950. Min Range: -7.3950
Max Act: 6.6763. Min Act: -0.1700
Data Index: 3787130 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19