Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2464 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0364. Min Range: -7.0364
Max Act: 7.0364. Min Act: -0.1700
Data Index: 7096843 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0364. Min Range: -7.0364
Max Act: 7.0364. Min Act: -0.1700
Data Index: 4656616 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0364. Min Range: -7.0364
Max Act: 7.0364. Min Act: -0.1700
Data Index: 7799566 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0364. Min Range: -7.0364
Max Act: 7.0364. Min Act: -0.1700
Data Index: 798218 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.9739. Min Act: -0.1700
Data Index: 5694579 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.9426. Min Act: -0.1700
Data Index: 8247962 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.9426. Min Act: -0.1700
Data Index: 7541266 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.9114. Min Act: -0.1700
Data Index: 7633833 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.9114. Min Act: -0.1700
Data Index: 1234150 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.8801. Min Act: -0.1700
Data Index: 3740135 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.8801. Min Act: -0.1700
Data Index: 5961087 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.8801. Min Act: -0.1700
Data Index: 5438110 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.8489. Min Act: -0.1700
Data Index: 2387703 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.8801. Min Act: -0.1700
Data Index: 8462687 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.8489. Min Act: -0.1700
Data Index: 889163 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.8489. Min Act: -0.1700
Data Index: 8237800 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.8489. Min Act: -0.1700
Data Index: 6858115 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.8489. Min Act: -0.1700
Data Index: 3405599 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.8489. Min Act: -0.1700
Data Index: 4473437 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0364. Min Range: -7.0364
Max Act: 6.8489. Min Act: -0.1700
Data Index: 4384361 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19