Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3487 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.8866. Min Act: -0.1700
Data Index: 3512435 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.5741. Min Act: -0.1700
Data Index: 5336634 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.5116. Min Act: -0.1700
Data Index: 6072935 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.5429. Min Act: -0.1700
Data Index: 5706279 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.4804. Min Act: -0.1700
Data Index: 1592683 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.3866. Min Act: -0.1700
Data Index: 7402053 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.3866. Min Act: -0.1700
Data Index: 2854656 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.3554. Min Act: -0.1700
Data Index: 936152 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.3866. Min Act: -0.1700
Data Index: 981326 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.3241. Min Act: -0.1700
Data Index: 5325998 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.3554. Min Act: -0.1700
Data Index: 2497512 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.2929. Min Act: -0.1700
Data Index: 3338165 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.2616. Min Act: -0.1700
Data Index: 997965 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.2616. Min Act: -0.1700
Data Index: 2854645 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.2304. Min Act: -0.1700
Data Index: 6600320 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.2616. Min Act: -0.1700
Data Index: 5808775 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.2616. Min Act: -0.1700
Data Index: 2884749 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.2304. Min Act: -0.1700
Data Index: 8490618 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.2616. Min Act: -0.1700
Data Index: 390103 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8866. Min Range: -4.8866
Max Act: 4.2304. Min Act: -0.1700
Data Index: 4729182 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19