Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 438 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3671. Min Act: -0.1656
Data Index: 4987888 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3582. Min Act: -0.1699
Data Index: 8213705 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3494. Min Act: -0.1694
Data Index: 2155890 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3406. Min Act: -0.1664
Data Index: 5537982 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3318. Min Act: -0.1699
Data Index: 1758570 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3406. Min Act: -0.1698
Data Index: 330474 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3230. Min Act: -0.1648
Data Index: 1884974 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3318. Min Act: -0.1692
Data Index: 1255726 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3318. Min Act: -0.1698
Data Index: 4763573 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3053. Min Act: -0.1700
Data Index: 8029328 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3142. Min Act: -0.1700
Data Index: 3173074 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3230. Min Act: -0.1689
Data Index: 4820511 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3230. Min Act: -0.1700
Data Index: 1812368 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3230. Min Act: -0.1676
Data Index: 7487206 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3230. Min Act: -0.1699
Data Index: 8007308 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3142. Min Act: -0.1700
Data Index: 1793521 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3142. Min Act: -0.1692
Data Index: 7567534 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3142. Min Act: -0.1692
Data Index: 4528550 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3230. Min Act: -0.1694
Data Index: 4892181 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3671. Min Range: -1.3671
Max Act: 1.3142. Min Act: -0.1690
Data Index: 4953908 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19