Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3923 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.4990. Min Act: -0.1700
Data Index: 3202360 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.4677. Min Act: -0.1700
Data Index: 3202361 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.4677. Min Act: -0.1700
Data Index: 3202362 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.4677. Min Act: -0.1700
Data Index: 7380201 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.4050. Min Act: -0.1700
Data Index: 1698412 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.4050. Min Act: -0.1700
Data Index: 2820634 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.4050. Min Act: -0.1700
Data Index: 8316179 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.4050. Min Act: -0.1700
Data Index: 6052306 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.4050. Min Act: -0.1700
Data Index: 4513440 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.3736. Min Act: -0.1700
Data Index: 6052308 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.3736. Min Act: -0.1700
Data Index: 1076083 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.3736. Min Act: -0.1700
Data Index: 2916595 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.3736. Min Act: -0.1700
Data Index: 1344462 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.3736. Min Act: -0.1700
Data Index: 210946 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.4050. Min Act: -0.1700
Data Index: 1716553 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.3736. Min Act: -0.1700
Data Index: 724540 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.3736. Min Act: -0.1700
Data Index: 724539 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.3736. Min Act: -0.1700
Data Index: 4729044 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.3423. Min Act: -0.1700
Data Index: 4108490 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4990. Min Range: -3.4990
Max Act: 3.3423. Min Act: -0.1700
Data Index: 2560892 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19