Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.8290. Min Act: -0.1700
Data Index: 8126898 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.7665. Min Act: -0.1700
Data Index: 1350469 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.7352. Min Act: -0.1700
Data Index: 8272069 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.7196. Min Act: -0.1700
Data Index: 2624994 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.7196. Min Act: -0.1700
Data Index: 8600601 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.6883. Min Act: -0.1700
Data Index: 3914759 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.6883. Min Act: -0.1700
Data Index: 912764 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.6883. Min Act: -0.1700
Data Index: 6765404 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.6726. Min Act: -0.1700
Data Index: 6297845 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.6414. Min Act: -0.1700
Data Index: 7948254 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.6257. Min Act: -0.1700
Data Index: 5038507 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.6101. Min Act: -0.1700
Data Index: 1065006 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.6101. Min Act: -0.1700
Data Index: 2523305 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.5788. Min Act: -0.1700
Data Index: 6896937 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.6101. Min Act: -0.1700
Data Index: 7147978 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.5788. Min Act: -0.1700
Data Index: 722267 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.5474. Min Act: -0.1700
Data Index: 3936138 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.5474. Min Act: -0.1700
Data Index: 1009950 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.5474. Min Act: -0.1700
Data Index: 8319639 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8290. Min Range: -3.8290
Max Act: 3.5631. Min Act: -0.1700
Data Index: 7210872 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19