Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2603 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.9064. Min Act: -0.1700
Data Index: 7549720 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.8751. Min Act: -0.1700
Data Index: 5786466 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.8438. Min Act: -0.1700
Data Index: 5001607 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.8438. Min Act: -0.1700
Data Index: 4748054 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.8438. Min Act: -0.1700
Data Index: 3773941 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.8126. Min Act: -0.1700
Data Index: 2719595 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.7813. Min Act: -0.1700
Data Index: 5759948 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.7813. Min Act: -0.1700
Data Index: 7039478 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.7500. Min Act: -0.1700
Data Index: 3419127 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.7813. Min Act: -0.1700
Data Index: 2223918 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.7500. Min Act: -0.1700
Data Index: 5978937 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.7500. Min Act: -0.1700
Data Index: 6227266 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.7500. Min Act: -0.1700
Data Index: 5890798 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.7500. Min Act: -0.1700
Data Index: 6646023 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.7500. Min Act: -0.1700
Data Index: 1712730 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.7500. Min Act: -0.1700
Data Index: 6679178 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.7500. Min Act: -0.1700
Data Index: 1645288 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.7187. Min Act: -0.1700
Data Index: 3053259 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.7500. Min Act: -0.1700
Data Index: 5295588 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9064. Min Range: -3.9064
Max Act: 3.7500. Min Act: -0.1700
Data Index: 1919724 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19