Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3999 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.4722. Min Act: -0.1700
Data Index: 1087730 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.3930. Min Act: -0.1697
Data Index: 6269691 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.3665. Min Act: -0.1579
Data Index: 6645479 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.3489. Min Act: -0.1700
Data Index: 1593611 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.3313. Min Act: -0.1655
Data Index: 8415479 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.3313. Min Act: -0.1700
Data Index: 6054527 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.3136. Min Act: -0.1657
Data Index: 5504383 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.3048. Min Act: -0.1694
Data Index: 1194576 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.2960. Min Act: -0.1699
Data Index: 7533111 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.2872. Min Act: -0.1685
Data Index: 2920522 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.2872. Min Act: -0.1596
Data Index: 4835294 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.2960. Min Act: -0.1699
Data Index: 1194574 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.2783. Min Act: -0.1694
Data Index: 6259969 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.2872. Min Act: -0.1519
Data Index: 6412257 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.2783. Min Act: -0.1697
Data Index: 2949918 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.2695. Min Act: -0.1697
Data Index: 7463368 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.2695. Min Act: -0.1604
Data Index: 4393660 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.2695. Min Act: -0.1700
Data Index: 6659407 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.2607. Min Act: -0.1700
Data Index: 3964604 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4722. Min Range: -1.4722
Max Act: 1.2695. Min Act: -0.1640
Data Index: 6168365 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19