Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5309 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.5870. Min Act: -0.1700
Data Index: 2552462 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.4308. Min Act: -0.1700
Data Index: 3224349 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.3995. Min Act: -0.1700
Data Index: 5413425 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.3370. Min Act: -0.1700
Data Index: 2216217 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.3683. Min Act: -0.1700
Data Index: 6096117 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.2745. Min Act: -0.1700
Data Index: 207902 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.2745. Min Act: -0.1700
Data Index: 5413427 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.2745. Min Act: -0.1700
Data Index: 3406300 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.2433. Min Act: -0.1700
Data Index: 8534669 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.1807. Min Act: -0.1700
Data Index: 4278045 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.1807. Min Act: -0.1700
Data Index: 2063594 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.1807. Min Act: -0.1700
Data Index: 6096119 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.1495. Min Act: -0.1700
Data Index: 4914171 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.1495. Min Act: -0.1700
Data Index: 6851411 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.1495. Min Act: -0.1700
Data Index: 6331787 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.1182. Min Act: -0.1700
Data Index: 551025 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.0870. Min Act: -0.1700
Data Index: 4858687 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.1182. Min Act: -0.1700
Data Index: 4652525 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.1182. Min Act: -0.1700
Data Index: 253012 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5870. Min Range: -4.5870
Max Act: 4.1182. Min Act: -0.1700
Data Index: 8050300 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19