Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2111 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2960. Min Range: -6.2960
Max Act: 6.2960. Min Act: -0.1700
Data Index: 1373413 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2960. Min Range: -6.2960
Max Act: 6.1710. Min Act: -0.1700
Data Index: 7559688 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2960. Min Range: -6.2960
Max Act: 6.1085. Min Act: -0.1700
Data Index: 1399137 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2960. Min Range: -6.2960
Max Act: 6.0460. Min Act: -0.1700
Data Index: 2000269 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2960. Min Range: -6.2960
Max Act: 6.0148. Min Act: -0.1700
Data Index: 8559837 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2960. Min Range: -6.2960
Max Act: 6.0148. Min Act: -0.1700
Data Index: 143673 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2960. Min Range: -6.2960
Max Act: 6.0460. Min Act: -0.1700
Data Index: 1193655 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2960. Min Range: -6.2960
Max Act: 6.0148. Min Act: -0.1700
Data Index: 6317548 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2960. Min Range: -6.2960
Max Act: 5.9523. Min Act: -0.1700
Data Index: 2859032 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2960. Min Range: -6.2960
Max Act: 5.9835. Min Act: -0.1700
Data Index: 5233702 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2960. Min Range: -6.2960
Max Act: 5.9210. Min Act: -0.1700
Data Index: 4716319 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2960. Min Range: -6.2960
Max Act: 5.9523. Min Act: -0.1700
Data Index: 856324 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2960. Min Range: -6.2960
Max Act: 5.9210. Min Act: -0.1700
Data Index: 257923 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2960. Min Range: -6.2960
Max Act: 5.9523. Min Act: -0.1700
Data Index: 1885525 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2960. Min Range: -6.2960
Max Act: 5.9210. Min Act: -0.1700
Data Index: 8125313 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2960. Min Range: -6.2960
Max Act: 5.9210. Min Act: -0.1700
Data Index: 1225959 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2960. Min Range: -6.2960
Max Act: 5.8898. Min Act: -0.1700
Data Index: 6574053 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2960. Min Range: -6.2960
Max Act: 5.8898. Min Act: -0.1700
Data Index: 2861527 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2960. Min Range: -6.2960
Max Act: 5.8898. Min Act: -0.1700
Data Index: 3267528 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2960. Min Range: -6.2960
Max Act: 5.8898. Min Act: -0.1700
Data Index: 8641900 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19