Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 575 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.8460. Min Act: -0.1700
Data Index: 5635399 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.8772. Min Act: -0.1700
Data Index: 5615125 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.8772. Min Act: -0.1700
Data Index: 1350030 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.8147. Min Act: -0.1700
Data Index: 6318494 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.6585. Min Act: -0.1700
Data Index: 1966380 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.5960. Min Act: -0.1700
Data Index: 6740433 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.5647. Min Act: -0.1700
Data Index: 2255873 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.5335. Min Act: -0.1700
Data Index: 5518265 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.5335. Min Act: -0.1700
Data Index: 2892294 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.4085. Min Act: -0.1700
Data Index: 896640 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.4085. Min Act: -0.1700
Data Index: 457345 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.4397. Min Act: -0.1700
Data Index: 6363844 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.4085. Min Act: -0.1700
Data Index: 2603617 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.4085. Min Act: -0.1700
Data Index: 4506268 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.3772. Min Act: -0.1700
Data Index: 8540467 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.3772. Min Act: -0.1700
Data Index: 2594636 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.3460. Min Act: -0.1700
Data Index: 327867 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.3460. Min Act: -0.1700
Data Index: 8295817 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.3460. Min Act: -0.1700
Data Index: 6178599 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8772. Min Range: -5.8772
Max Act: 5.3147. Min Act: -0.1700
Data Index: 4054242 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19