Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 778 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.4711. Min Act: -0.1700
Data Index: 7200137 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.4398. Min Act: -0.1700
Data Index: 2061159 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.4086. Min Act: -0.1700
Data Index: 2179986 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.3148. Min Act: -0.1700
Data Index: 6524205 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.2836. Min Act: -0.1700
Data Index: 7912759 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.2836. Min Act: -0.1700
Data Index: 813951 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.2523. Min Act: -0.1700
Data Index: 2590711 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1898. Min Act: -0.1700
Data Index: 3236669 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1898. Min Act: -0.1700
Data Index: 1714958 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1898. Min Act: -0.1700
Data Index: 7481629 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1273. Min Act: -0.1700
Data Index: 7432955 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1586. Min Act: -0.1700
Data Index: 874122 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1898. Min Act: -0.1700
Data Index: 7127102 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1586. Min Act: -0.1700
Data Index: 5429037 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1586. Min Act: -0.1700
Data Index: 7278790 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1898. Min Act: -0.1700
Data Index: 4561746 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1273. Min Act: -0.1700
Data Index: 8271803 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1586. Min Act: -0.1700
Data Index: 2652976 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1273. Min Act: -0.1700
Data Index: 5890293 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.0648. Min Act: -0.1700
Data Index: 1593983 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19