Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1422 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.7999. Min Act: -0.1700
Data Index: 5403483 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.7374. Min Act: -0.1700
Data Index: 1773606 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.6749. Min Act: -0.1700
Data Index: 5620614 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.6436. Min Act: -0.1700
Data Index: 5789851 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.6436. Min Act: -0.1700
Data Index: 1371863 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.6436. Min Act: -0.1700
Data Index: 2103974 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.6436. Min Act: -0.1700
Data Index: 6476540 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.6436. Min Act: -0.1700
Data Index: 7813521 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.6436. Min Act: -0.1700
Data Index: 8169243 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.6436. Min Act: -0.1700
Data Index: 3224683 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.6124. Min Act: -0.1700
Data Index: 689630 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.6124. Min Act: -0.1700
Data Index: 6181840 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.6124. Min Act: -0.1700
Data Index: 2214990 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.6124. Min Act: -0.1700
Data Index: 3443789 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.6436. Min Act: -0.1700
Data Index: 1211259 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.6124. Min Act: -0.1700
Data Index: 7918367 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.6124. Min Act: -0.1700
Data Index: 4381609 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.6124. Min Act: -0.1700
Data Index: 3653829 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.6124. Min Act: -0.1700
Data Index: 4058586 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7999. Min Range: -5.7999
Max Act: 5.5811. Min Act: -0.1700
Data Index: 5574141 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19