Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1679 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.7773. Min Act: -0.1700
Data Index: 4121916 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.7148. Min Act: -0.1700
Data Index: 3804695 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.5898. Min Act: -0.1700
Data Index: 7064451 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.5585. Min Act: -0.1700
Data Index: 7100208 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.4023. Min Act: -0.1700
Data Index: 3286 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.3710. Min Act: -0.1700
Data Index: 476278 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.3085. Min Act: -0.1700
Data Index: 142297 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.3085. Min Act: -0.1700
Data Index: 8420202 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.2148. Min Act: -0.1700
Data Index: 5923401 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.1835. Min Act: -0.1700
Data Index: 6065659 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.1523. Min Act: -0.1700
Data Index: 7916057 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.1835. Min Act: -0.1700
Data Index: 4825978 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.1210. Min Act: -0.1700
Data Index: 7180559 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.0898. Min Act: -0.1700
Data Index: 1133966 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7773. Min Range: -5.7773
Max Act: 4.9960. Min Act: -0.1700
Data Index: 3786797 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.0585. Min Act: -0.1700
Data Index: 7496718 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.0585. Min Act: -0.1700
Data Index: 1144320 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.0273. Min Act: -0.1700
Data Index: 5223739 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7773. Min Range: -5.7773
Max Act: 5.0585. Min Act: -0.1700
Data Index: 3551593 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7773. Min Range: -5.7773
Max Act: 4.9960. Min Act: -0.1700
Data Index: 7490765 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19