Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 950 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.9553. Min Act: -0.1700
Data Index: 3391659 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.7678. Min Act: -0.1700
Data Index: 1121257 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.7678. Min Act: -0.1700
Data Index: 2812591 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.7678. Min Act: -0.1700
Data Index: 1726930 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.6741. Min Act: -0.1700
Data Index: 7186607 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.7678. Min Act: -0.1700
Data Index: 7189527 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.7053. Min Act: -0.1700
Data Index: 1911226 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.7053. Min Act: -0.1700
Data Index: 69193 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.6428. Min Act: -0.1700
Data Index: 3338785 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.5803. Min Act: -0.1700
Data Index: 6989145 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.4866. Min Act: -0.1700
Data Index: 3986029 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.4866. Min Act: -0.1700
Data Index: 4944778 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.4241. Min Act: -0.1700
Data Index: 1637306 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.4866. Min Act: -0.1700
Data Index: 3348943 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.4553. Min Act: -0.1700
Data Index: 1496597 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.4553. Min Act: -0.1700
Data Index: 5077495 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.4241. Min Act: -0.1700
Data Index: 6144941 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.4553. Min Act: -0.1700
Data Index: 5562423 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.3928. Min Act: -0.1700
Data Index: 6534952 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9553. Min Range: -4.9553
Max Act: 4.3616. Min Act: -0.1700
Data Index: 1915052 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19