Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.8848. Min Act: -0.1700
Data Index: 1160708 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.8536. Min Act: -0.1700
Data Index: 2638523 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.7286. Min Act: -0.1700
Data Index: 7822220 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.6348. Min Act: -0.1700
Data Index: 6330610 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.6661. Min Act: -0.1700
Data Index: 1394245 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.6348. Min Act: -0.1700
Data Index: 8427925 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.6348. Min Act: -0.1700
Data Index: 2771856 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.6036. Min Act: -0.1700
Data Index: 6281100 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.6036. Min Act: -0.1700
Data Index: 4855340 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.6036. Min Act: -0.1700
Data Index: 556873 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.5723. Min Act: -0.1700
Data Index: 5378356 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.5411. Min Act: -0.1700
Data Index: 2039215 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.5411. Min Act: -0.1700
Data Index: 7415843 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.5411. Min Act: -0.1700
Data Index: 5490345 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.5098. Min Act: -0.1700
Data Index: 8786881 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.4786. Min Act: -0.1700
Data Index: 7183019 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.4786. Min Act: -0.1700
Data Index: 2563570 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.4473. Min Act: -0.1700
Data Index: 3009137 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.4786. Min Act: -0.1700
Data Index: 110689 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8848. Min Range: -6.8848
Max Act: 6.4786. Min Act: -0.1700
Data Index: 7147507 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19