Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 848 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.2293. Min Act: -0.1700
Data Index: 8415713 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.0730. Min Act: -0.1700
Data Index: 371961 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.0418. Min Act: -0.1700
Data Index: 46163 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.0418. Min Act: -0.1700
Data Index: 5730714 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.0105. Min Act: -0.1700
Data Index: 4860122 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.0105. Min Act: -0.1700
Data Index: 950684 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2293. Min Range: -5.2293
Max Act: 5.0105. Min Act: -0.1700
Data Index: 1816264 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.9168. Min Act: -0.1700
Data Index: 867714 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.9480. Min Act: -0.1700
Data Index: 2016576 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.9168. Min Act: -0.1700
Data Index: 5715730 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.8855. Min Act: -0.1700
Data Index: 6266444 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.8855. Min Act: -0.1700
Data Index: 8303010 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.8543. Min Act: -0.1700
Data Index: 3196961 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.8230. Min Act: -0.1700
Data Index: 106623 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.7918. Min Act: -0.1700
Data Index: 6754206 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.8230. Min Act: -0.1700
Data Index: 1258732 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.8230. Min Act: -0.1700
Data Index: 6298013 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.7918. Min Act: -0.1700
Data Index: 4115822 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.7918. Min Act: -0.1700
Data Index: 6532378 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2293. Min Range: -5.2293
Max Act: 4.7918. Min Act: -0.1700
Data Index: 3451216 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19