Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1120 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.6045. Min Act: -0.1700
Data Index: 7089691 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.5420. Min Act: -0.1700
Data Index: 2279745 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.5420. Min Act: -0.1700
Data Index: 5642904 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.6045. Min Act: -0.1700
Data Index: 135181 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.4795. Min Act: -0.1700
Data Index: 4641817 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.3857. Min Act: -0.1700
Data Index: 3465568 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.3857. Min Act: -0.1700
Data Index: 6921927 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.3857. Min Act: -0.1700
Data Index: 859428 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.3232. Min Act: -0.1700
Data Index: 2197178 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.2920. Min Act: -0.1700
Data Index: 5456371 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.2607. Min Act: -0.1700
Data Index: 4579966 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.2607. Min Act: -0.1700
Data Index: 1249793 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.1670. Min Act: -0.1700
Data Index: 4686100 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.1670. Min Act: -0.1700
Data Index: 4298853 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.2295. Min Act: -0.1700
Data Index: 3203798 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.2295. Min Act: -0.1700
Data Index: 4209852 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.1982. Min Act: -0.1700
Data Index: 1542337 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.1357. Min Act: -0.1700
Data Index: 1310975 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.1982. Min Act: -0.1700
Data Index: 5030251 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6045. Min Range: -8.6045
Max Act: 8.2920. Min Act: -0.1700
Data Index: 626018 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19