Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3515 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.2530. Min Act: -0.1700
Data Index: 248854 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.2530. Min Act: -0.1700
Data Index: 2255195 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.2218. Min Act: -0.1700
Data Index: 3492449 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.1905. Min Act: -0.1700
Data Index: 8005726 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.1905. Min Act: -0.1700
Data Index: 4043540 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.1905. Min Act: -0.1700
Data Index: 6713652 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.1592. Min Act: -0.1700
Data Index: 2141544 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.1592. Min Act: -0.1700
Data Index: 6833842 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.1592. Min Act: -0.1699
Data Index: 1235701 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.1592. Min Act: -0.1700
Data Index: 7841755 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.1592. Min Act: -0.1700
Data Index: 1593983 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.1592. Min Act: -0.1700
Data Index: 5955890 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.1592. Min Act: -0.1694
Data Index: 1038416 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.1592. Min Act: -0.1700
Data Index: 414666 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.1592. Min Act: -0.1692
Data Index: 4614610 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.1592. Min Act: -0.1700
Data Index: 4830761 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.1280. Min Act: -0.1700
Data Index: 4179405 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.1280. Min Act: -0.1700
Data Index: 2704424 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.1280. Min Act: -0.1700
Data Index: 5134129 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2530. Min Range: -4.2530
Max Act: 4.1280. Min Act: -0.1700
Data Index: 1592252 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19