Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 24 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.3005. Min Act: -0.1700
Data Index: 3997429 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2740. Min Act: -0.1700
Data Index: 1687670 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2652. Min Act: -0.1695
Data Index: 7545030 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2476. Min Act: -0.1697
Data Index: 697811 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2476. Min Act: -0.1698
Data Index: 6220234 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2476. Min Act: -0.1693
Data Index: 5451776 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2476. Min Act: -0.1700
Data Index: 1806136 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2387. Min Act: -0.1700
Data Index: 6884030 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2387. Min Act: -0.1698
Data Index: 449243 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2299. Min Act: -0.1662
Data Index: 680588 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2387. Min Act: -0.1698
Data Index: 7662648 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2211. Min Act: -0.1700
Data Index: 1466126 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2211. Min Act: -0.1699
Data Index: 6229592 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2211. Min Act: -0.1651
Data Index: 6287354 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2123. Min Act: -0.1700
Data Index: 1884318 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2123. Min Act: -0.1700
Data Index: 8353156 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2035. Min Act: -0.1700
Data Index: 3121844 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2123. Min Act: -0.1700
Data Index: 177124 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2123. Min Act: -0.1693
Data Index: 5526777 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3005. Min Range: -1.3005
Max Act: 1.2123. Min Act: -0.1698
Data Index: 2091835 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19