Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3782 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.5408. Min Act: -0.1700
Data Index: 5897673 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.5095. Min Act: -0.1700
Data Index: 6607183 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4470. Min Act: -0.1700
Data Index: 7010827 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4783. Min Act: -0.1700
Data Index: 5659065 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4470. Min Act: -0.1700
Data Index: 7770592 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4158. Min Act: -0.1700
Data Index: 5024099 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4470. Min Act: -0.1700
Data Index: 4345283 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4470. Min Act: -0.1700
Data Index: 7307456 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4470. Min Act: -0.1700
Data Index: 6530395 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4470. Min Act: -0.1700
Data Index: 6719902 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4470. Min Act: -0.1700
Data Index: 2878765 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4158. Min Act: -0.1700
Data Index: 7632803 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4158. Min Act: -0.1700
Data Index: 388149 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.3845. Min Act: -0.1700
Data Index: 5857019 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.3845. Min Act: -0.1700
Data Index: 7887064 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.3845. Min Act: -0.1700
Data Index: 8152711 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.3845. Min Act: -0.1700
Data Index: 5744155 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4158. Min Act: -0.1700
Data Index: 6753779 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.4158. Min Act: -0.1700
Data Index: 5339909 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5408. Min Range: -4.5408
Max Act: 4.3845. Min Act: -0.1700
Data Index: 5063262 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19