Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3514 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4709. Min Range: -6.4709
Max Act: 6.4709. Min Act: -0.1700
Data Index: 2450551 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4709. Min Range: -6.4709
Max Act: 6.0647. Min Act: -0.1700
Data Index: 2237031 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4709. Min Range: -6.4709
Max Act: 6.0647. Min Act: -0.1700
Data Index: 7484722 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4709. Min Range: -6.4709
Max Act: 6.0022. Min Act: -0.1700
Data Index: 5484786 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.9709. Min Act: -0.1700
Data Index: 2237038 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.9709. Min Act: -0.1700
Data Index: 2473791 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.9397. Min Act: -0.1700
Data Index: 8363845 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.8772. Min Act: -0.1700
Data Index: 3802223 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.9084. Min Act: -0.1700
Data Index: 7620261 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.8459. Min Act: -0.1700
Data Index: 2473786 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.8147. Min Act: -0.1700
Data Index: 6776021 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.8459. Min Act: -0.1700
Data Index: 7345219 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.8147. Min Act: -0.1700
Data Index: 5418417 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.8147. Min Act: -0.1700
Data Index: 8772481 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.7834. Min Act: -0.1700
Data Index: 8732456 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.8147. Min Act: -0.1700
Data Index: 5817772 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.7834. Min Act: -0.1700
Data Index: 5744656 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.7522. Min Act: -0.1700
Data Index: 7620260 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.7522. Min Act: -0.1700
Data Index: 2512768 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.7209. Min Act: -0.1700
Data Index: 1250443 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19