Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 838 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.9431. Min Act: -0.1700
Data Index: 1646154 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.9744. Min Act: -0.1700
Data Index: 8757593 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.9431. Min Act: -0.1700
Data Index: 8089580 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.8806. Min Act: -0.1700
Data Index: 7662357 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.8806. Min Act: -0.1700
Data Index: 6217946 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.8806. Min Act: -0.1700
Data Index: 3166332 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.9119. Min Act: -0.1700
Data Index: 7044446 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.9119. Min Act: -0.1700
Data Index: 3933635 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.8806. Min Act: -0.1700
Data Index: 325645 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.8494. Min Act: -0.1700
Data Index: 3232409 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.8494. Min Act: -0.1700
Data Index: 1171807 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.7244. Min Act: -0.1700
Data Index: 2894367 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.7556. Min Act: -0.1700
Data Index: 5098561 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.7244. Min Act: -0.1700
Data Index: 212083 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.7244. Min Act: -0.1700
Data Index: 1047789 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.7244. Min Act: -0.1700
Data Index: 5006507 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.6931. Min Act: -0.1700
Data Index: 5923049 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.6931. Min Act: -0.1700
Data Index: 4212230 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.6619. Min Act: -0.1700
Data Index: 3122521 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9744. Min Range: -6.9744
Max Act: 6.6619. Min Act: -0.1700
Data Index: 3132410 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19