Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1708 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.5585. Min Act: -0.1700
Data Index: 7523232 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.5585. Min Act: -0.1700
Data Index: 2139098 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.5273. Min Act: -0.1700
Data Index: 1843110 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.4335. Min Act: -0.1700
Data Index: 5603823 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.3398. Min Act: -0.1700
Data Index: 253650 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.3398. Min Act: -0.1700
Data Index: 5151952 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.2460. Min Act: -0.1700
Data Index: 8008014 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.2773. Min Act: -0.1700
Data Index: 4631980 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.2773. Min Act: -0.1700
Data Index: 1098928 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.2773. Min Act: -0.1700
Data Index: 8649502 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.2773. Min Act: -0.1700
Data Index: 5187674 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.2773. Min Act: -0.1700
Data Index: 4886754 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.2460. Min Act: -0.1700
Data Index: 7896228 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.2460. Min Act: -0.1700
Data Index: 507814 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.2460. Min Act: -0.1700
Data Index: 1528032 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.2148. Min Act: -0.1700
Data Index: 5491454 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.2148. Min Act: -0.1700
Data Index: 4742190 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.2148. Min Act: -0.1700
Data Index: 4395882 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.1835. Min Act: -0.1700
Data Index: 1769928 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5585. Min Range: -5.5585
Max Act: 5.1523. Min Act: -0.1700
Data Index: 3103505 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19