Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 482 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.3201. Min Act: -0.1700
Data Index: 478654 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.2888. Min Act: -0.1700
Data Index: 5618986 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.2888. Min Act: -0.1700
Data Index: 2704367 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.2888. Min Act: -0.1700
Data Index: 2401555 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.1950. Min Act: -0.1700
Data Index: 8558483 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.2263. Min Act: -0.1700
Data Index: 683028 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.1950. Min Act: -0.1700
Data Index: 4589240 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.1950. Min Act: -0.1700
Data Index: 5034760 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.1950. Min Act: -0.1700
Data Index: 7292082 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.1638. Min Act: -0.1700
Data Index: 108885 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.1325. Min Act: -0.1700
Data Index: 3913148 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.1013. Min Act: -0.1700
Data Index: 4293841 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.1013. Min Act: -0.1700
Data Index: 5196821 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.1013. Min Act: -0.1700
Data Index: 7687310 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.1013. Min Act: -0.1700
Data Index: 3294833 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.0700. Min Act: -0.1700
Data Index: 2426828 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.0700. Min Act: -0.1700
Data Index: 4075078 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.0388. Min Act: -0.1700
Data Index: 3519061 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.0388. Min Act: -0.1700
Data Index: 7453239 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3201. Min Range: -4.3201
Max Act: 4.0388. Min Act: -0.1700
Data Index: 4268689 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19