Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5236 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.2538. Min Act: -0.1700
Data Index: 4821764 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.1601. Min Act: -0.1700
Data Index: 8551561 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.1601. Min Act: -0.1700
Data Index: 8106382 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.1288. Min Act: -0.1700
Data Index: 5851422 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.1288. Min Act: -0.1700
Data Index: 2555529 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0976. Min Act: -0.1700
Data Index: 243067 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0976. Min Act: -0.1700
Data Index: 6555125 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0976. Min Act: -0.1700
Data Index: 5898008 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0976. Min Act: -0.1700
Data Index: 5734495 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0663. Min Act: -0.1700
Data Index: 7334995 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0351. Min Act: -0.1700
Data Index: 6531019 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2538. Min Range: -5.2538
Max Act: 4.9726. Min Act: -0.1700
Data Index: 6394213 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2538. Min Range: -5.2538
Max Act: 4.9726. Min Act: -0.1700
Data Index: 49095 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2538. Min Range: -5.2538
Max Act: 4.9726. Min Act: -0.1700
Data Index: 6333400 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2538. Min Range: -5.2538
Max Act: 4.9726. Min Act: -0.1700
Data Index: 7864132 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2538. Min Range: -5.2538
Max Act: 4.9726. Min Act: -0.1700
Data Index: 2108415 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2538. Min Range: -5.2538
Max Act: 4.9726. Min Act: -0.1700
Data Index: 3232803 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2538. Min Range: -5.2538
Max Act: 4.9726. Min Act: -0.1700
Data Index: 2409089 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2538. Min Range: -5.2538
Max Act: 4.9413. Min Act: -0.1700
Data Index: 3128601 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2538. Min Range: -5.2538
Max Act: 4.9413. Min Act: -0.1700
Data Index: 1160877 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19