Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2629 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.5610. Min Act: -0.1700
Data Index: 2770317 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.4047. Min Act: -0.1700
Data Index: 1120382 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.4047. Min Act: -0.1700
Data Index: 4273244 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.3735. Min Act: -0.1700
Data Index: 8034581 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.3422. Min Act: -0.1700
Data Index: 2964784 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.3110. Min Act: -0.1700
Data Index: 8416480 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.2485. Min Act: -0.1700
Data Index: 5158345 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.2485. Min Act: -0.1700
Data Index: 4028503 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.2485. Min Act: -0.1700
Data Index: 297077 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.2485. Min Act: -0.1700
Data Index: 4394814 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.2172. Min Act: -0.1700
Data Index: 68237 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.1860. Min Act: -0.1700
Data Index: 4144088 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.2172. Min Act: -0.1700
Data Index: 4816567 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.1860. Min Act: -0.1700
Data Index: 211448 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.1860. Min Act: -0.1700
Data Index: 4743036 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.1860. Min Act: -0.1700
Data Index: 8832916 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.1860. Min Act: -0.1700
Data Index: 8205881 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.1860. Min Act: -0.1700
Data Index: 6628757 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.1860. Min Act: -0.1700
Data Index: 7042430 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5610. Min Range: -6.5610
Max Act: 6.1860. Min Act: -0.1700
Data Index: 2151265 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19