Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3772. Min Range: -7.3772
Max Act: 7.3772. Min Act: -0.1700
Data Index: 6694794 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3772. Min Range: -7.3772
Max Act: 7.1585. Min Act: -0.1700
Data Index: 7227015 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3772. Min Range: -7.3772
Max Act: 7.1272. Min Act: -0.1700
Data Index: 5793429 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3772. Min Range: -7.3772
Max Act: 7.0960. Min Act: -0.1700
Data Index: 4980093 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3772. Min Range: -7.3772
Max Act: 7.0960. Min Act: -0.1700
Data Index: 4568649 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3772. Min Range: -7.3772
Max Act: 7.0647. Min Act: -0.1700
Data Index: 7267654 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3772. Min Range: -7.3772
Max Act: 7.0335. Min Act: -0.1700
Data Index: 4282769 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3772. Min Range: -7.3772
Max Act: 7.0335. Min Act: -0.1700
Data Index: 4225027 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3772. Min Range: -7.3772
Max Act: 7.0335. Min Act: -0.1700
Data Index: 7552523 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3772. Min Range: -7.3772
Max Act: 7.0335. Min Act: -0.1700
Data Index: 7958075 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3772. Min Range: -7.3772
Max Act: 7.0022. Min Act: -0.1700
Data Index: 2443474 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3772. Min Range: -7.3772
Max Act: 7.0022. Min Act: -0.1700
Data Index: 7614013 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3772. Min Range: -7.3772
Max Act: 7.0335. Min Act: -0.1700
Data Index: 4190622 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3772. Min Range: -7.3772
Max Act: 6.9710. Min Act: -0.1700
Data Index: 4693686 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3772. Min Range: -7.3772
Max Act: 6.9710. Min Act: -0.1700
Data Index: 1973686 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3772. Min Range: -7.3772
Max Act: 6.9397. Min Act: -0.1700
Data Index: 2658727 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3772. Min Range: -7.3772
Max Act: 6.9397. Min Act: -0.1700
Data Index: 8125865 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3772. Min Range: -7.3772
Max Act: 6.9397. Min Act: -0.1700
Data Index: 6537231 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3772. Min Range: -7.3772
Max Act: 6.8772. Min Act: -0.1700
Data Index: 4024440 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3772. Min Range: -7.3772
Max Act: 6.8772. Min Act: -0.1700
Data Index: 4517375 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19