Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2541 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.5245. Min Range: -15.5245
Max Act: 15.5245. Min Act: -0.1700
Data Index: 584459 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.5245. Min Range: -15.5245
Max Act: 15.3370. Min Act: -0.1700
Data Index: 162138 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.5245. Min Range: -15.5245
Max Act: 15.2120. Min Act: -0.1700
Data Index: 6419658 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.5245. Min Range: -15.5245
Max Act: 15.2745. Min Act: -0.1700
Data Index: 7059556 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.5245. Min Range: -15.5245
Max Act: 15.2120. Min Act: -0.1700
Data Index: 2377604 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.5245. Min Range: -15.5245
Max Act: 15.1495. Min Act: -0.1700
Data Index: 3749305 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.5245. Min Range: -15.5245
Max Act: 15.0870. Min Act: -0.1700
Data Index: 1497248 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.5245. Min Range: -15.5245
Max Act: 15.0245. Min Act: -0.1700
Data Index: 6643403 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.5245. Min Range: -15.5245
Max Act: 15.0245. Min Act: -0.1700
Data Index: 8029239 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.5245. Min Range: -15.5245
Max Act: 15.0245. Min Act: -0.1700
Data Index: 3825277 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.5245. Min Range: -15.5245
Max Act: 14.9620. Min Act: -0.1700
Data Index: 7903532 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.5245. Min Range: -15.5245
Max Act: 14.9620. Min Act: -0.1700
Data Index: 2007524 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.5245. Min Range: -15.5245
Max Act: 14.8995. Min Act: -0.1700
Data Index: 4450471 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.5245. Min Range: -15.5245
Max Act: 14.9620. Min Act: -0.1700
Data Index: 8752889 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.5245. Min Range: -15.5245
Max Act: 14.9620. Min Act: -0.1700
Data Index: 5773824 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.5245. Min Range: -15.5245
Max Act: 14.9620. Min Act: -0.1700
Data Index: 5112381 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.5245. Min Range: -15.5245
Max Act: 14.9620. Min Act: -0.1700
Data Index: 576656 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.5245. Min Range: -15.5245
Max Act: 14.8370. Min Act: -0.1700
Data Index: 173565 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.5245. Min Range: -15.5245
Max Act: 14.8995. Min Act: -0.1700
Data Index: 5052154 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.5245. Min Range: -15.5245
Max Act: 14.8370. Min Act: -0.1700
Data Index: 1670629 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19