Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2898 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.6317. Min Act: -0.1700
Data Index: 2422865 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.6317. Min Act: -0.1700
Data Index: 7917431 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.5692. Min Act: -0.1700
Data Index: 919381 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.3817. Min Act: -0.1700
Data Index: 5811432 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.3817. Min Act: -0.1700
Data Index: 6202439 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.3192. Min Act: -0.1700
Data Index: 3476596 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.3192. Min Act: -0.1700
Data Index: 8190962 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.2567. Min Act: -0.1700
Data Index: 5531471 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.2567. Min Act: -0.1700
Data Index: 2263339 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.2567. Min Act: -0.1700
Data Index: 5182969 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.2567. Min Act: -0.1700
Data Index: 6020735 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.1942. Min Act: -0.1700
Data Index: 8326259 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.1942. Min Act: -0.1700
Data Index: 1657865 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.1317. Min Act: -0.1700
Data Index: 374820 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.1317. Min Act: -0.1700
Data Index: 8189060 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.1317. Min Act: -0.1700
Data Index: 6358537 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.1317. Min Act: -0.1700
Data Index: 5665284 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.1317. Min Act: -0.1700
Data Index: 3524558 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.0692. Min Act: -0.1700
Data Index: 6195232 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6317. Min Range: -10.6317
Max Act: 10.0692. Min Act: -0.1700
Data Index: 7967943 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19