Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 920 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.6517. Min Act: -0.1700
Data Index: 2332776 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.4955. Min Act: -0.1700
Data Index: 174914 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.4642. Min Act: -0.1700
Data Index: 5320121 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.4330. Min Act: -0.1700
Data Index: 1238517 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.4017. Min Act: -0.1700
Data Index: 6277508 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.4017. Min Act: -0.1700
Data Index: 8540839 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.3705. Min Act: -0.1700
Data Index: 2277784 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.3705. Min Act: -0.1700
Data Index: 4158119 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.3705. Min Act: -0.1700
Data Index: 8814685 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.3080. Min Act: -0.1700
Data Index: 4500139 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.3080. Min Act: -0.1700
Data Index: 6759851 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.3080. Min Act: -0.1700
Data Index: 613508 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.2767. Min Act: -0.1700
Data Index: 8828181 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.2767. Min Act: -0.1700
Data Index: 6649638 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.2767. Min Act: -0.1700
Data Index: 8521894 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.2455. Min Act: -0.1700
Data Index: 6223677 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.2455. Min Act: -0.1700
Data Index: 3380300 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.2455. Min Act: -0.1700
Data Index: 5607126 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.2455. Min Act: -0.1700
Data Index: 6963050 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6517. Min Range: -5.6517
Max Act: 5.2142. Min Act: -0.1700
Data Index: 3911279 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19