Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3491 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1419. Min Range: -5.1419
Max Act: 5.1419. Min Act: -0.1700
Data Index: 4206342 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1419. Min Range: -5.1419
Max Act: 5.1106. Min Act: -0.1700
Data Index: 6674059 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1419. Min Range: -5.1419
Max Act: 5.1106. Min Act: -0.1700
Data Index: 6843846 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1419. Min Range: -5.1419
Max Act: 5.0481. Min Act: -0.1700
Data Index: 4479103 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1419. Min Range: -5.1419
Max Act: 5.0169. Min Act: -0.1698
Data Index: 1477620 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1419. Min Range: -5.1419
Max Act: 5.0169. Min Act: -0.1700
Data Index: 2850748 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1419. Min Range: -5.1419
Max Act: 4.9231. Min Act: -0.1700
Data Index: 6140837 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1419. Min Range: -5.1419
Max Act: 4.8919. Min Act: -0.1700
Data Index: 445389 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1419. Min Range: -5.1419
Max Act: 4.9231. Min Act: -0.1700
Data Index: 6112963 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1419. Min Range: -5.1419
Max Act: 4.8606. Min Act: -0.1700
Data Index: 6140844 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1419. Min Range: -5.1419
Max Act: 4.8294. Min Act: -0.1698
Data Index: 1477592 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1419. Min Range: -5.1419
Max Act: 4.8294. Min Act: -0.1699
Data Index: 6140846 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1419. Min Range: -5.1419
Max Act: 4.7669. Min Act: -0.1700
Data Index: 6140848 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1419. Min Range: -5.1419
Max Act: 4.7669. Min Act: -0.1700
Data Index: 2787235 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1419. Min Range: -5.1419
Max Act: 4.7356. Min Act: -0.1700
Data Index: 1058803 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1419. Min Range: -5.1419
Max Act: 4.7356. Min Act: -0.1700
Data Index: 5709322 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1419. Min Range: -5.1419
Max Act: 4.7356. Min Act: -0.1700
Data Index: 1477609 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1419. Min Range: -5.1419
Max Act: 4.7356. Min Act: -0.1696
Data Index: 1477595 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1419. Min Range: -5.1419
Max Act: 4.7044. Min Act: -0.1700
Data Index: 1477610 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1419. Min Range: -5.1419
Max Act: 4.7044. Min Act: -0.1700
Data Index: 6140832 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19