Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7858. Min Act: -0.1700
Data Index: 1211950 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7858. Min Act: -0.1700
Data Index: 8241709 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7858. Min Act: -0.1700
Data Index: 3250910 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7858. Min Act: -0.1700
Data Index: 7930277 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7858. Min Act: -0.1700
Data Index: 4791738 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7858. Min Act: -0.1700
Data Index: 2215425 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7858. Min Act: -0.1700
Data Index: 2087741 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7858. Min Act: -0.1700
Data Index: 4578965 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7858. Min Act: -0.1700
Data Index: 6223447 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7858. Min Act: -0.1700
Data Index: 4120967 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7858. Min Act: -0.1700
Data Index: 1932279 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7858. Min Act: -0.1700
Data Index: 573520 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7858. Min Act: -0.1700
Data Index: 2821207 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7858. Min Act: -0.1700
Data Index: 4928088 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7858. Min Act: -0.1700
Data Index: 4858642 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7858. Min Act: -0.1700
Data Index: 3361367 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7545. Min Act: -0.1700
Data Index: 880935 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7545. Min Act: -0.1700
Data Index: 1949516 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7545. Min Act: -0.1700
Data Index: 5135462 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7545. Min Act: -0.1700
Data Index: 7407671 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19