Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2562 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.3378. Min Act: -0.1700
Data Index: 5791917 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.3690. Min Act: -0.1700
Data Index: 7979610 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.3378. Min Act: -0.1700
Data Index: 3054049 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.2753. Min Act: -0.1700
Data Index: 8776746 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.2753. Min Act: -0.1700
Data Index: 5982756 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.2440. Min Act: -0.1700
Data Index: 846749 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1815. Min Act: -0.1700
Data Index: 6154308 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1815. Min Act: -0.1700
Data Index: 8776749 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1503. Min Act: -0.1700
Data Index: 8532545 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.1190. Min Act: -0.1700
Data Index: 1238035 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.0878. Min Act: -0.1700
Data Index: 4578704 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.0565. Min Act: -0.1700
Data Index: 4343970 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.0253. Min Act: -0.1700
Data Index: 551750 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.0253. Min Act: -0.1700
Data Index: 3287121 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.9940. Min Act: -0.1700
Data Index: 7976333 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.9940. Min Act: -0.1700
Data Index: 2546196 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3690. Min Range: -5.3690
Max Act: 5.0253. Min Act: -0.1700
Data Index: 3195483 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.9628. Min Act: -0.1700
Data Index: 7040985 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.9315. Min Act: -0.1700
Data Index: 8027919 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3690. Min Range: -5.3690
Max Act: 4.9315. Min Act: -0.1700
Data Index: 3205894 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19