Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6039 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.9423. Min Act: -0.1700
Data Index: 1251021 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.8798. Min Act: -0.1700
Data Index: 622151 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.6610. Min Act: -0.1700
Data Index: 7261722 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.6610. Min Act: -0.1700
Data Index: 1439443 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.6610. Min Act: -0.1700
Data Index: 7778541 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.5360. Min Act: -0.1700
Data Index: 1702002 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.5360. Min Act: -0.1700
Data Index: 3652520 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.5048. Min Act: -0.1700
Data Index: 1407542 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.4735. Min Act: -0.1700
Data Index: 2711983 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.4423. Min Act: -0.1700
Data Index: 4656567 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.4423. Min Act: -0.1700
Data Index: 5694788 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.3798. Min Act: -0.1700
Data Index: 2792318 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.3485. Min Act: -0.1700
Data Index: 854719 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.3173. Min Act: -0.1700
Data Index: 3763247 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.3173. Min Act: -0.1700
Data Index: 4390719 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.2860. Min Act: -0.1700
Data Index: 2016467 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.2860. Min Act: -0.1700
Data Index: 4858267 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.2860. Min Act: -0.1700
Data Index: 5859505 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.2860. Min Act: -0.1700
Data Index: 3345750 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9423. Min Range: -6.9423
Max Act: 6.2860. Min Act: -0.1700
Data Index: 775119 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19