Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 676 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2118. Min Range: -5.2118
Max Act: 5.2118. Min Act: -0.1700
Data Index: 3298565 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2118. Min Range: -5.2118
Max Act: 5.1493. Min Act: -0.1700
Data Index: 129061 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.9618. Min Act: -0.1700
Data Index: 8575357 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.9930. Min Act: -0.1700
Data Index: 4209276 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.9618. Min Act: -0.1700
Data Index: 8792959 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.9618. Min Act: -0.1700
Data Index: 4015657 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.9305. Min Act: -0.1700
Data Index: 960957 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.8993. Min Act: -0.1700
Data Index: 4151083 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.8680. Min Act: -0.1700
Data Index: 611465 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.8680. Min Act: -0.1700
Data Index: 3660369 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.8368. Min Act: -0.1700
Data Index: 4558209 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.8368. Min Act: -0.1700
Data Index: 1624537 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.8055. Min Act: -0.1700
Data Index: 222846 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.8368. Min Act: -0.1700
Data Index: 726555 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.8680. Min Act: -0.1700
Data Index: 4681507 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.7743. Min Act: -0.1700
Data Index: 7826907 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.8055. Min Act: -0.1700
Data Index: 3510692 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.7743. Min Act: -0.1700
Data Index: 7377389 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.7743. Min Act: -0.1700
Data Index: 2202026 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2118. Min Range: -5.2118
Max Act: 4.7743. Min Act: -0.1700
Data Index: 6277971 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19