Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3171 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.6531. Min Act: -0.1700
Data Index: 6804304 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.5593. Min Act: -0.1699
Data Index: 1894994 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.5593. Min Act: -0.1700
Data Index: 5606503 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.5281. Min Act: -0.1700
Data Index: 2146239 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.4968. Min Act: -0.1700
Data Index: 2705969 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.4343. Min Act: -0.1700
Data Index: 3534263 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.4343. Min Act: -0.1700
Data Index: 2499760 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.4343. Min Act: -0.1700
Data Index: 1355952 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.4031. Min Act: -0.1700
Data Index: 1658700 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.4031. Min Act: -0.1700
Data Index: 4306885 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.3718. Min Act: -0.1700
Data Index: 1847745 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.3406. Min Act: -0.1700
Data Index: 2705968 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.3406. Min Act: -0.1700
Data Index: 5769562 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.3406. Min Act: -0.1700
Data Index: 4607116 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.3406. Min Act: -0.1700
Data Index: 987046 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.3406. Min Act: -0.1700
Data Index: 2015180 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.3093. Min Act: -0.1700
Data Index: 5915811 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.3093. Min Act: -0.1700
Data Index: 827824 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.3406. Min Act: -0.1700
Data Index: 1478921 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6531. Min Range: -5.6531
Max Act: 5.3093. Min Act: -0.1700
Data Index: 5041180 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19