Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.7591. Min Act: -0.1700
Data Index: 8066759 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.7591. Min Act: -0.1700
Data Index: 3015940 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.7278. Min Act: -0.1700
Data Index: 6596273 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.7278. Min Act: -0.1700
Data Index: 2985235 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.7278. Min Act: -0.1700
Data Index: 2043863 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.6653. Min Act: -0.1700
Data Index: 4467134 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.6966. Min Act: -0.1700
Data Index: 2094433 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.6966. Min Act: -0.1700
Data Index: 2668124 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.6966. Min Act: -0.1700
Data Index: 3445209 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.6966. Min Act: -0.1700
Data Index: 1826884 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.6966. Min Act: -0.1700
Data Index: 2051785 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.6966. Min Act: -0.1700
Data Index: 8701693 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.6966. Min Act: -0.1700
Data Index: 2822543 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.6966. Min Act: -0.1700
Data Index: 5905903 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.6966. Min Act: -0.1700
Data Index: 5418803 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.6653. Min Act: -0.1700
Data Index: 4415538 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.6653. Min Act: -0.1700
Data Index: 3279613 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.6341. Min Act: -0.1700
Data Index: 2545329 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.6653. Min Act: -0.1700
Data Index: 1385943 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7591. Min Range: -5.7591
Max Act: 5.6653. Min Act: -0.1700
Data Index: 3319397 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19