Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3676 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.7120. Min Act: -0.1700
Data Index: 8712865 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.5870. Min Act: -0.1700
Data Index: 7576692 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.4933. Min Act: -0.1700
Data Index: 8412598 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.4308. Min Act: -0.1700
Data Index: 5285052 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.3995. Min Act: -0.1700
Data Index: 8040709 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.3683. Min Act: -0.1700
Data Index: 2990823 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.3683. Min Act: -0.1700
Data Index: 7843004 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.3370. Min Act: -0.1700
Data Index: 6597446 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.3370. Min Act: -0.1700
Data Index: 3749958 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.3058. Min Act: -0.1700
Data Index: 6782490 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.3058. Min Act: -0.1700
Data Index: 4181592 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.3058. Min Act: -0.1700
Data Index: 7819776 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.2745. Min Act: -0.1700
Data Index: 5988194 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.2745. Min Act: -0.1700
Data Index: 3642745 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.2433. Min Act: -0.1700
Data Index: 1633097 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.2745. Min Act: -0.1700
Data Index: 1394732 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.1808. Min Act: -0.1700
Data Index: 7888856 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.2120. Min Act: -0.1700
Data Index: 612383 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.2120. Min Act: -0.1700
Data Index: 7104286 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7120. Min Range: -5.7120
Max Act: 5.1808. Min Act: -0.1700
Data Index: 7888855 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19