Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3875 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.7065. Min Act: -0.1700
Data Index: 1333118 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.6752. Min Act: -0.1700
Data Index: 7641151 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.6127. Min Act: -0.1700
Data Index: 2210273 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.5815. Min Act: -0.1700
Data Index: 2723180 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.5190. Min Act: -0.1700
Data Index: 1577887 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.5190. Min Act: -0.1700
Data Index: 7495586 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.4877. Min Act: -0.1700
Data Index: 6141903 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.4877. Min Act: -0.1700
Data Index: 6178065 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.4565. Min Act: -0.1700
Data Index: 4364899 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.4877. Min Act: -0.1700
Data Index: 8458321 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.4877. Min Act: -0.1700
Data Index: 8677875 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.4565. Min Act: -0.1700
Data Index: 4168757 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.4565. Min Act: -0.1700
Data Index: 6110842 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.4877. Min Act: -0.1700
Data Index: 8407605 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.4565. Min Act: -0.1700
Data Index: 4295494 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.3940. Min Act: -0.1700
Data Index: 3009328 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.4252. Min Act: -0.1700
Data Index: 6302557 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.4252. Min Act: -0.1700
Data Index: 5554154 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.3940. Min Act: -0.1700
Data Index: 6923068 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7065. Min Range: -5.7065
Max Act: 5.3940. Min Act: -0.1700
Data Index: 7097873 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19