Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2839 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.4308. Min Act: -0.1700
Data Index: 6856314 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.2745. Min Act: -0.1700
Data Index: 1864878 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.2433. Min Act: -0.1700
Data Index: 4294438 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.1808. Min Act: -0.1700
Data Index: 8534284 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.2120. Min Act: -0.1700
Data Index: 2342137 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.1808. Min Act: -0.1700
Data Index: 2464406 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.1808. Min Act: -0.1700
Data Index: 6987115 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.1808. Min Act: -0.1700
Data Index: 83833 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.1808. Min Act: -0.1700
Data Index: 6861545 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.1182. Min Act: -0.1700
Data Index: 4987293 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.1182. Min Act: -0.1700
Data Index: 858385 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.1182. Min Act: -0.1700
Data Index: 2859232 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.1182. Min Act: -0.1700
Data Index: 2659943 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.0870. Min Act: -0.1700
Data Index: 1106778 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.0870. Min Act: -0.1700
Data Index: 449102 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.0870. Min Act: -0.1700
Data Index: 2720252 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.0870. Min Act: -0.1700
Data Index: 6726112 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.0870. Min Act: -0.1700
Data Index: 1999898 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.0557. Min Act: -0.1700
Data Index: 1164430 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4308. Min Range: -4.4308
Max Act: 4.0870. Min Act: -0.1700
Data Index: 2915768 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19