Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2656 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3005. Min Range: -7.3005
Max Act: 7.3005. Min Act: -0.1700
Data Index: 7793936 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3005. Min Range: -7.3005
Max Act: 7.2067. Min Act: -0.1700
Data Index: 7449220 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.9880. Min Act: -0.1700
Data Index: 7247549 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.9567. Min Act: -0.1700
Data Index: 3903962 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.9255. Min Act: -0.1700
Data Index: 6609561 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.9255. Min Act: -0.1700
Data Index: 6998730 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.9255. Min Act: -0.1700
Data Index: 27143 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.9255. Min Act: -0.1700
Data Index: 5373545 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.9255. Min Act: -0.1700
Data Index: 7004005 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.8630. Min Act: -0.1700
Data Index: 7826180 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.8942. Min Act: -0.1700
Data Index: 7220373 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.8630. Min Act: -0.1700
Data Index: 2853309 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.8005. Min Act: -0.1700
Data Index: 8715547 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.8005. Min Act: -0.1700
Data Index: 1887363 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.7692. Min Act: -0.1700
Data Index: 5631447 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.7380. Min Act: -0.1700
Data Index: 517515 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.7067. Min Act: -0.1700
Data Index: 5275548 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.7380. Min Act: -0.1700
Data Index: 5798333 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.7692. Min Act: -0.1700
Data Index: 4109745 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3005. Min Range: -7.3005
Max Act: 6.6755. Min Act: -0.1700
Data Index: 3168500 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19