Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2394 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.9036. Min Act: -0.1700
Data Index: 496017 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.8099. Min Act: -0.1700
Data Index: 186436 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.8099. Min Act: -0.1699
Data Index: 1892956 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.8099. Min Act: -0.1700
Data Index: 147647 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.7786. Min Act: -0.1691
Data Index: 4677545 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.7474. Min Act: -0.1700
Data Index: 6765981 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.7786. Min Act: -0.1700
Data Index: 3443451 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.7786. Min Act: -0.1700
Data Index: 4334989 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.7474. Min Act: -0.1700
Data Index: 8614318 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.7474. Min Act: -0.1697
Data Index: 4978296 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.7474. Min Act: -0.1700
Data Index: 4183037 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.7161. Min Act: -0.1700
Data Index: 2786704 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.7474. Min Act: -0.1700
Data Index: 2967756 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.7474. Min Act: -0.1700
Data Index: 1000235 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.7474. Min Act: -0.1700
Data Index: 2867556 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.7161. Min Act: -0.1698
Data Index: 21838 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.7474. Min Act: -0.1700
Data Index: 3809155 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.7474. Min Act: -0.1700
Data Index: 7711402 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.7474. Min Act: -0.1700
Data Index: 2473914 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9036. Min Range: -4.9036
Max Act: 4.7474. Min Act: -0.1700
Data Index: 9553 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19