Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2549. Min Range: -6.2549
Max Act: 6.2549. Min Act: -0.1700
Data Index: 4559532 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2549. Min Range: -6.2549
Max Act: 6.0987. Min Act: -0.1700
Data Index: 8219502 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.9112. Min Act: -0.1700
Data Index: 5612701 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.8487. Min Act: -0.1700
Data Index: 6593246 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.7549. Min Act: -0.1700
Data Index: 1306885 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.7237. Min Act: -0.1700
Data Index: 4755158 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.7237. Min Act: -0.1700
Data Index: 7919790 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.6924. Min Act: -0.1700
Data Index: 6116670 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.6612. Min Act: -0.1700
Data Index: 635447 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.6924. Min Act: -0.1700
Data Index: 1481003 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.6299. Min Act: -0.1700
Data Index: 7245868 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.6299. Min Act: -0.1700
Data Index: 1113021 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.6299. Min Act: -0.1700
Data Index: 7439443 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.5674. Min Act: -0.1700
Data Index: 2153969 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.5674. Min Act: -0.1700
Data Index: 8320036 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.5674. Min Act: -0.1700
Data Index: 1530745 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.5362. Min Act: -0.1700
Data Index: 3573014 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.5362. Min Act: -0.1700
Data Index: 887744 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.5049. Min Act: -0.1700
Data Index: 7152615 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2549. Min Range: -6.2549
Max Act: 5.4737. Min Act: -0.1700
Data Index: 5236492 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19