Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 55 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2023. Min Range: -5.2023
Max Act: 5.2023. Min Act: -0.1700
Data Index: 8357171 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2023. Min Range: -5.2023
Max Act: 5.1710. Min Act: -0.1700
Data Index: 5565094 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2023. Min Range: -5.2023
Max Act: 5.0773. Min Act: -0.1700
Data Index: 3408679 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2023. Min Range: -5.2023
Max Act: 5.0773. Min Act: -0.1700
Data Index: 3637824 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2023. Min Range: -5.2023
Max Act: 5.0460. Min Act: -0.1700
Data Index: 4281900 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2023. Min Range: -5.2023
Max Act: 5.0460. Min Act: -0.1700
Data Index: 8771888 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2023. Min Range: -5.2023
Max Act: 5.0148. Min Act: -0.1700
Data Index: 4199107 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2023. Min Range: -5.2023
Max Act: 5.0148. Min Act: -0.1700
Data Index: 659687 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2023. Min Range: -5.2023
Max Act: 5.0148. Min Act: -0.1700
Data Index: 7085614 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2023. Min Range: -5.2023
Max Act: 4.9835. Min Act: -0.1699
Data Index: 673663 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2023. Min Range: -5.2023
Max Act: 4.9523. Min Act: -0.1700
Data Index: 2765921 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2023. Min Range: -5.2023
Max Act: 4.9835. Min Act: -0.1700
Data Index: 4431766 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2023. Min Range: -5.2023
Max Act: 4.9835. Min Act: -0.1700
Data Index: 1468043 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2023. Min Range: -5.2023
Max Act: 4.9523. Min Act: -0.1700
Data Index: 3499523 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2023. Min Range: -5.2023
Max Act: 4.9523. Min Act: -0.1700
Data Index: 5816970 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2023. Min Range: -5.2023
Max Act: 4.9523. Min Act: -0.1700
Data Index: 1560381 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2023. Min Range: -5.2023
Max Act: 4.9523. Min Act: -0.1700
Data Index: 2693424 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2023. Min Range: -5.2023
Max Act: 4.9523. Min Act: -0.1700
Data Index: 3925645 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2023. Min Range: -5.2023
Max Act: 4.9210. Min Act: -0.1700
Data Index: 5093584 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2023. Min Range: -5.2023
Max Act: 4.9523. Min Act: -0.1700
Data Index: 4153118 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19