Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3901 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.9425. Min Act: -0.1700
Data Index: 4677978 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.8488. Min Act: -0.1700
Data Index: 434284 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.7863. Min Act: -0.1700
Data Index: 3255252 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.7238. Min Act: -0.1700
Data Index: 444482 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.7550. Min Act: -0.1700
Data Index: 5475551 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.6613. Min Act: -0.1700
Data Index: 2125833 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.6300. Min Act: -0.1700
Data Index: 6466184 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.5675. Min Act: -0.1700
Data Index: 6730251 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.5363. Min Act: -0.1700
Data Index: 6398472 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.5363. Min Act: -0.1700
Data Index: 5045511 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.5050. Min Act: -0.1700
Data Index: 3728296 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.4738. Min Act: -0.1700
Data Index: 3165236 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.4738. Min Act: -0.1700
Data Index: 7815147 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.4425. Min Act: -0.1700
Data Index: 3506822 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.4425. Min Act: -0.1700
Data Index: 5680056 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.3800. Min Act: -0.1700
Data Index: 6957261 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.4113. Min Act: -0.1700
Data Index: 7951377 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.4113. Min Act: -0.1700
Data Index: 3294939 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.3800. Min Act: -0.1700
Data Index: 6694218 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9425. Min Range: -6.9425
Max Act: 6.3488. Min Act: -0.1700
Data Index: 5030186 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19