Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 181 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1735. Min Range: -6.1735
Max Act: 6.1735. Min Act: -0.1700
Data Index: 2159106 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1735. Min Range: -6.1735
Max Act: 6.0798. Min Act: -0.1700
Data Index: 7052381 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.9860. Min Act: -0.1700
Data Index: 2433510 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.9860. Min Act: -0.1700
Data Index: 3244984 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.9860. Min Act: -0.1700
Data Index: 4590659 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.9860. Min Act: -0.1700
Data Index: 2201195 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.8923. Min Act: -0.1700
Data Index: 7748432 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.8923. Min Act: -0.1700
Data Index: 5975277 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.8923. Min Act: -0.1700
Data Index: 7056956 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.8610. Min Act: -0.1700
Data Index: 1178956 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.8610. Min Act: -0.1700
Data Index: 6059899 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.8610. Min Act: -0.1700
Data Index: 2457356 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.8610. Min Act: -0.1700
Data Index: 5934786 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.8298. Min Act: -0.1700
Data Index: 8083691 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.8298. Min Act: -0.1700
Data Index: 8551654 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.8298. Min Act: -0.1700
Data Index: 2111199 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.7985. Min Act: -0.1700
Data Index: 7870538 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.7985. Min Act: -0.1700
Data Index: 1716947 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.7985. Min Act: -0.1700
Data Index: 6948497 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1735. Min Range: -6.1735
Max Act: 5.7985. Min Act: -0.1700
Data Index: 5507006 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19