Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1685 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.4825. Min Act: -0.1700
Data Index: 3024709 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.2013. Min Act: -0.1700
Data Index: 1288329 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.2013. Min Act: -0.1700
Data Index: 8330293 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.1700. Min Act: -0.1700
Data Index: 591727 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.1700. Min Act: -0.1700
Data Index: 6101462 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.0763. Min Act: -0.1700
Data Index: 1028179 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.0450. Min Act: -0.1700
Data Index: 3236680 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.0138. Min Act: -0.1700
Data Index: 1665661 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4825. Min Range: -6.4825
Max Act: 6.0450. Min Act: -0.1700
Data Index: 8415808 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4825. Min Range: -6.4825
Max Act: 5.9825. Min Act: -0.1700
Data Index: 6518123 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4825. Min Range: -6.4825
Max Act: 5.9200. Min Act: -0.1700
Data Index: 319118 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4825. Min Range: -6.4825
Max Act: 5.9200. Min Act: -0.1700
Data Index: 3885568 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4825. Min Range: -6.4825
Max Act: 5.9200. Min Act: -0.1700
Data Index: 5986649 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4825. Min Range: -6.4825
Max Act: 5.8575. Min Act: -0.1700
Data Index: 7273327 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4825. Min Range: -6.4825
Max Act: 5.8575. Min Act: -0.1700
Data Index: 4059395 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4825. Min Range: -6.4825
Max Act: 5.8575. Min Act: -0.1700
Data Index: 1260263 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4825. Min Range: -6.4825
Max Act: 5.8263. Min Act: -0.1700
Data Index: 4672712 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4825. Min Range: -6.4825
Max Act: 5.8263. Min Act: -0.1700
Data Index: 3011651 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4825. Min Range: -6.4825
Max Act: 5.7950. Min Act: -0.1700
Data Index: 3743635 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4825. Min Range: -6.4825
Max Act: 5.7950. Min Act: -0.1700
Data Index: 4914676 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19