Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.4006. Min Act: -0.1700
Data Index: 2379877 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.4319. Min Act: -0.1700
Data Index: 8305800 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.4319. Min Act: -0.1700
Data Index: 6603404 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.3694. Min Act: -0.1700
Data Index: 8206491 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.3694. Min Act: -0.1700
Data Index: 6858780 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.2756. Min Act: -0.1700
Data Index: 2379873 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.3069. Min Act: -0.1700
Data Index: 5542703 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.2131. Min Act: -0.1700
Data Index: 4183302 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.1819. Min Act: -0.1700
Data Index: 5374411 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.1819. Min Act: -0.1700
Data Index: 4095923 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.1194. Min Act: -0.1700
Data Index: 6602017 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.1506. Min Act: -0.1700
Data Index: 6858779 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.1506. Min Act: -0.1700
Data Index: 3070824 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.1506. Min Act: -0.1700
Data Index: 4533300 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.1506. Min Act: -0.1700
Data Index: 3305019 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.0881. Min Act: -0.1700
Data Index: 986365 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.0881. Min Act: -0.1700
Data Index: 3070826 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.0881. Min Act: -0.1700
Data Index: 6603403 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.0881. Min Act: -0.1700
Data Index: 813563 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4319. Min Range: -5.4319
Max Act: 5.0881. Min Act: -0.1700
Data Index: 1188641 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19