Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 984 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.6890. Min Act: -0.1700
Data Index: 7759772 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.6890. Min Act: -0.1700
Data Index: 7731025 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.5328. Min Act: -0.1700
Data Index: 3252532 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.3765. Min Act: -0.1700
Data Index: 8135799 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.3453. Min Act: -0.1700
Data Index: 6057650 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.3453. Min Act: -0.1700
Data Index: 5407395 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.2515. Min Act: -0.1700
Data Index: 1006385 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.1890. Min Act: -0.1700
Data Index: 5960636 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.1890. Min Act: -0.1700
Data Index: 4490927 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.1890. Min Act: -0.1700
Data Index: 5740660 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.1265. Min Act: -0.1700
Data Index: 6015741 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.0640. Min Act: -0.1700
Data Index: 6232866 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.0953. Min Act: -0.1700
Data Index: 6470608 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.0640. Min Act: -0.1700
Data Index: 7637939 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.0953. Min Act: -0.1700
Data Index: 144945 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.0953. Min Act: -0.1700
Data Index: 5929724 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.0328. Min Act: -0.1700
Data Index: 28497 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.0328. Min Act: -0.1700
Data Index: 8735328 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.0640. Min Act: -0.1700
Data Index: 2347830 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6890. Min Range: -6.6890
Max Act: 6.0640. Min Act: -0.1700
Data Index: 4286523 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19