Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.8996. Min Act: -0.1698
Data Index: 6216572 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.6808. Min Act: -0.1700
Data Index: 1038862 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.5246. Min Act: -0.1700
Data Index: 4795226 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.5246. Min Act: -0.1700
Data Index: 6970021 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.5871. Min Act: -0.1700
Data Index: 7529572 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.5558. Min Act: -0.1699
Data Index: 1517962 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.4933. Min Act: -0.1700
Data Index: 7474446 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.4933. Min Act: -0.1700
Data Index: 113732 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.4933. Min Act: -0.1700
Data Index: 8444736 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.4933. Min Act: -0.1700
Data Index: 2488259 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.5246. Min Act: -0.1700
Data Index: 1028060 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.4621. Min Act: -0.1700
Data Index: 7881457 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.4621. Min Act: -0.1700
Data Index: 4864659 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.3996. Min Act: -0.1700
Data Index: 1668851 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.4308. Min Act: -0.1700
Data Index: 2764355 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.3683. Min Act: -0.1700
Data Index: 765392 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.3683. Min Act: -0.1700
Data Index: 6244582 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.3371. Min Act: -0.1700
Data Index: 5811695 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.3371. Min Act: -0.1700
Data Index: 3095873 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8996. Min Range: -4.8996
Max Act: 4.3683. Min Act: -0.1700
Data Index: 6548835 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19