Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 200 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2890. Min Act: -0.1665
Data Index: 3157282 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2890. Min Act: -0.1692
Data Index: 4451954 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2802. Min Act: -0.1699
Data Index: 6084403 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2802. Min Act: -0.1661
Data Index: 8815844 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2714. Min Act: -0.1395
Data Index: 2787102 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2626. Min Act: -0.1693
Data Index: 7519933 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2626. Min Act: -0.1682
Data Index: 3222245 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2449. Min Act: -0.1700
Data Index: 5816497 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2537. Min Act: -0.1699
Data Index: 1037870 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2449. Min Act: -0.1686
Data Index: 4895603 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2537. Min Act: -0.1588
Data Index: 568373 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2449. Min Act: -0.1465
Data Index: 6835166 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2449. Min Act: -0.1689
Data Index: 3983641 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2449. Min Act: -0.1607
Data Index: 8745531 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2537. Min Act: -0.1683
Data Index: 4374463 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2361. Min Act: -0.1566
Data Index: 2861594 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2361. Min Act: -0.1525
Data Index: 8069965 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2361. Min Act: -0.1699
Data Index: 4526622 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2361. Min Act: -0.1527
Data Index: 5323430 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2890. Min Range: -1.2890
Max Act: 1.2273. Min Act: -0.1661
Data Index: 7957690 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19