Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3265 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.5391. Min Act: -0.1700
Data Index: 439291 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.5079. Min Act: -0.1700
Data Index: 8284630 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.4454. Min Act: -0.1700
Data Index: 7412499 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.4454. Min Act: -0.1700
Data Index: 2083332 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.4141. Min Act: -0.1700
Data Index: 5432546 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.4141. Min Act: -0.1700
Data Index: 8185666 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.4141. Min Act: -0.1700
Data Index: 7873065 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.3204. Min Act: -0.1697
Data Index: 6943578 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.3204. Min Act: -0.1698
Data Index: 8475136 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.3204. Min Act: -0.1700
Data Index: 2468926 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.2891. Min Act: -0.1695
Data Index: 3192754 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.2891. Min Act: -0.1670
Data Index: 6267926 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.2891. Min Act: -0.1700
Data Index: 3071320 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.2579. Min Act: -0.1700
Data Index: 3742585 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.2891. Min Act: -0.1700
Data Index: 3260969 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.2579. Min Act: -0.1700
Data Index: 87452 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.2266. Min Act: -0.1699
Data Index: 5525525 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.2266. Min Act: -0.1699
Data Index: 4897277 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.1954. Min Act: -0.1700
Data Index: 6052046 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5391. Min Range: -5.5391
Max Act: 5.2266. Min Act: -0.1700
Data Index: 3555157 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19