Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2885 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1974. Min Range: -7.1974
Max Act: 7.1974. Min Act: -0.1700
Data Index: 213792 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1974. Min Range: -7.1974
Max Act: 7.0412. Min Act: -0.1700
Data Index: 475339 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.8849. Min Act: -0.1700
Data Index: 5271985 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.8224. Min Act: -0.1700
Data Index: 3875352 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.7912. Min Act: -0.1700
Data Index: 5457925 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.7287. Min Act: -0.1700
Data Index: 3284237 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.7287. Min Act: -0.1700
Data Index: 3810636 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.6349. Min Act: -0.1700
Data Index: 1740399 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.6349. Min Act: -0.1700
Data Index: 5118141 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.6349. Min Act: -0.1700
Data Index: 8083565 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.6349. Min Act: -0.1700
Data Index: 7624753 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.6037. Min Act: -0.1700
Data Index: 967525 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.5724. Min Act: -0.1700
Data Index: 8189069 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.5724. Min Act: -0.1700
Data Index: 4668159 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.5724. Min Act: -0.1700
Data Index: 8636722 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.5724. Min Act: -0.1700
Data Index: 4393144 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.5724. Min Act: -0.1700
Data Index: 2955906 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.5724. Min Act: -0.1700
Data Index: 7106092 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.5724. Min Act: -0.1700
Data Index: 8110614 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1974. Min Range: -7.1974
Max Act: 6.5724. Min Act: -0.1700
Data Index: 50089 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19