Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1276 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6240. Min Range: -7.6240
Max Act: 7.6240. Min Act: -0.1700
Data Index: 7269643 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6240. Min Range: -7.6240
Max Act: 7.4990. Min Act: -0.1700
Data Index: 2443437 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6240. Min Range: -7.6240
Max Act: 7.4365. Min Act: -0.1700
Data Index: 289853 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6240. Min Range: -7.6240
Max Act: 7.4365. Min Act: -0.1700
Data Index: 1620579 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6240. Min Range: -7.6240
Max Act: 7.2803. Min Act: -0.1700
Data Index: 3425470 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6240. Min Range: -7.6240
Max Act: 7.1865. Min Act: -0.1700
Data Index: 4647047 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6240. Min Range: -7.6240
Max Act: 7.0928. Min Act: -0.1700
Data Index: 7222199 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6240. Min Range: -7.6240
Max Act: 6.9990. Min Act: -0.1700
Data Index: 4622665 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6240. Min Range: -7.6240
Max Act: 6.9678. Min Act: -0.1700
Data Index: 7086384 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6240. Min Range: -7.6240
Max Act: 6.9678. Min Act: -0.1700
Data Index: 4307740 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6240. Min Range: -7.6240
Max Act: 6.9053. Min Act: -0.1700
Data Index: 4512001 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6240. Min Range: -7.6240
Max Act: 6.9365. Min Act: -0.1700
Data Index: 1287709 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6240. Min Range: -7.6240
Max Act: 6.9365. Min Act: -0.1700
Data Index: 2411864 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6240. Min Range: -7.6240
Max Act: 6.9053. Min Act: -0.1700
Data Index: 348630 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6240. Min Range: -7.6240
Max Act: 6.8740. Min Act: -0.1700
Data Index: 239300 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6240. Min Range: -7.6240
Max Act: 6.8740. Min Act: -0.1700
Data Index: 652237 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6240. Min Range: -7.6240
Max Act: 6.8428. Min Act: -0.1700
Data Index: 5093851 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6240. Min Range: -7.6240
Max Act: 6.8428. Min Act: -0.1700
Data Index: 5822517 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6240. Min Range: -7.6240
Max Act: 6.7803. Min Act: -0.1700
Data Index: 203183 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6240. Min Range: -7.6240
Max Act: 6.8115. Min Act: -0.1700
Data Index: 7256045 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19