Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3075 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2106. Min Range: -6.2106
Max Act: 6.2106. Min Act: -0.1700
Data Index: 3806205 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2106. Min Range: -6.2106
Max Act: 6.0544. Min Act: -0.1700
Data Index: 164200 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.9294. Min Act: -0.1700
Data Index: 945611 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.8981. Min Act: -0.1700
Data Index: 7884654 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.8669. Min Act: -0.1700
Data Index: 6137644 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.8669. Min Act: -0.1700
Data Index: 7049674 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.8356. Min Act: -0.1700
Data Index: 6697817 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.8356. Min Act: -0.1700
Data Index: 3113178 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.8356. Min Act: -0.1700
Data Index: 6006043 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.8669. Min Act: -0.1700
Data Index: 2913253 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.8044. Min Act: -0.1700
Data Index: 1578909 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.8044. Min Act: -0.1700
Data Index: 5484171 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.8044. Min Act: -0.1700
Data Index: 5869058 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.7731. Min Act: -0.1700
Data Index: 6477670 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.7731. Min Act: -0.1700
Data Index: 5141122 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.7419. Min Act: -0.1700
Data Index: 3981717 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.7419. Min Act: -0.1700
Data Index: 3622035 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.7106. Min Act: -0.1700
Data Index: 1769344 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.7419. Min Act: -0.1700
Data Index: 3625648 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2106. Min Range: -6.2106
Max Act: 5.7419. Min Act: -0.1700
Data Index: 4475216 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19