Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3758 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.8647. Min Act: -0.1700
Data Index: 2811473 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.8475. Min Act: -0.1700
Data Index: 7475852 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.8475. Min Act: -0.1700
Data Index: 50050 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.8304. Min Act: -0.1700
Data Index: 2141476 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.8304. Min Act: -0.1700
Data Index: 3328145 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.8132. Min Act: -0.1700
Data Index: 966468 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.8132. Min Act: -0.1700
Data Index: 7341242 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.8304. Min Act: -0.1700
Data Index: 1834598 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.7960. Min Act: -0.1700
Data Index: 4372140 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.7788. Min Act: -0.1700
Data Index: 6149313 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.7960. Min Act: -0.1700
Data Index: 8333753 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.7788. Min Act: -0.1700
Data Index: 2497824 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.7788. Min Act: -0.1700
Data Index: 2264306 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.7616. Min Act: -0.1700
Data Index: 8383268 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.7616. Min Act: -0.1700
Data Index: 5212180 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.7616. Min Act: -0.1700
Data Index: 4025348 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.7788. Min Act: -0.1700
Data Index: 7362155 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.7443. Min Act: -0.1700
Data Index: 6922432 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.7788. Min Act: -0.1700
Data Index: 4533016 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8647. Min Range: -1.8647
Max Act: 1.7443. Min Act: -0.1700
Data Index: 2601202 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19