Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3220 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.5386. Min Act: -0.1700
Data Index: 7459387 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.4761. Min Act: -0.1700
Data Index: 7052267 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.4761. Min Act: -0.1700
Data Index: 6268586 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.4761. Min Act: -0.1700
Data Index: 4147593 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.4449. Min Act: -0.1700
Data Index: 6341086 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.4136. Min Act: -0.1700
Data Index: 7563039 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.4136. Min Act: -0.1700
Data Index: 8626387 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.3199. Min Act: -0.1700
Data Index: 5401770 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.2886. Min Act: -0.1700
Data Index: 1387119 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.2886. Min Act: -0.1700
Data Index: 607731 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.3199. Min Act: -0.1700
Data Index: 5855628 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.2886. Min Act: -0.1700
Data Index: 2195007 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.2574. Min Act: -0.1700
Data Index: 1378223 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.2574. Min Act: -0.1700
Data Index: 6368960 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.2574. Min Act: -0.1700
Data Index: 5760856 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.2261. Min Act: -0.1700
Data Index: 5805356 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.2574. Min Act: -0.1700
Data Index: 3758893 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.2574. Min Act: -0.1700
Data Index: 3216481 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.2261. Min Act: -0.1700
Data Index: 4949566 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5386. Min Range: -4.5386
Max Act: 4.2261. Min Act: -0.1700
Data Index: 1398131 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19