Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5844 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.5144. Min Act: -0.1700
Data Index: 4147460 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.4832. Min Act: -0.1700
Data Index: 2946555 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.4207. Min Act: -0.1700
Data Index: 6383331 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.3894. Min Act: -0.1700
Data Index: 3232388 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.3582. Min Act: -0.1700
Data Index: 6800125 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.3894. Min Act: -0.1700
Data Index: 784076 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.3582. Min Act: -0.1700
Data Index: 3784597 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.3269. Min Act: -0.1700
Data Index: 404119 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.3269. Min Act: -0.1700
Data Index: 3693970 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.2957. Min Act: -0.1700
Data Index: 5342466 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.3269. Min Act: -0.1700
Data Index: 4727464 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.3269. Min Act: -0.1700
Data Index: 1685360 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.2644. Min Act: -0.1700
Data Index: 674927 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.2332. Min Act: -0.1700
Data Index: 2383261 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.2332. Min Act: -0.1700
Data Index: 3472435 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.2644. Min Act: -0.1700
Data Index: 5976378 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.2644. Min Act: -0.1700
Data Index: 4649890 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.2644. Min Act: -0.1700
Data Index: 1480600 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.2957. Min Act: -0.1700
Data Index: 1176410 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5144. Min Range: -5.5144
Max Act: 5.2644. Min Act: -0.1700
Data Index: 6541410 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19