Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 955 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0096. Min Range: -4.0096
Max Act: 4.0096. Min Act: -0.1700
Data Index: 91803 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.9783. Min Act: -0.1700
Data Index: 6823549 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.9783. Min Act: -0.1700
Data Index: 3422715 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.9470. Min Act: -0.1700
Data Index: 5112850 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.8845. Min Act: -0.1700
Data Index: 1248017 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.9158. Min Act: -0.1700
Data Index: 237095 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.8845. Min Act: -0.1700
Data Index: 402610 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.8532. Min Act: -0.1700
Data Index: 5747570 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.8845. Min Act: -0.1700
Data Index: 402625 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.8845. Min Act: -0.1700
Data Index: 4014806 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.8532. Min Act: -0.1700
Data Index: 5264636 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.8220. Min Act: -0.1700
Data Index: 5548225 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.8220. Min Act: -0.1700
Data Index: 5569953 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.8220. Min Act: -0.1700
Data Index: 5423534 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.7907. Min Act: -0.1700
Data Index: 6515786 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.7594. Min Act: -0.1700
Data Index: 4931104 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.7751. Min Act: -0.1700
Data Index: 2967116 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.7751. Min Act: -0.1700
Data Index: 824311 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.7438. Min Act: -0.1700
Data Index: 6483878 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0096. Min Range: -4.0096
Max Act: 3.7438. Min Act: -0.1700
Data Index: 6693032 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19