Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3147 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4099. Min Range: -6.4099
Max Act: 6.4099. Min Act: -0.1700
Data Index: 8527280 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4099. Min Range: -6.4099
Max Act: 6.3786. Min Act: -0.1700
Data Index: 385775 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4099. Min Range: -6.4099
Max Act: 6.2849. Min Act: -0.1700
Data Index: 7096470 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4099. Min Range: -6.4099
Max Act: 6.1599. Min Act: -0.1700
Data Index: 2765353 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4099. Min Range: -6.4099
Max Act: 6.1286. Min Act: -0.1700
Data Index: 6741671 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4099. Min Range: -6.4099
Max Act: 6.0974. Min Act: -0.1700
Data Index: 5783735 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4099. Min Range: -6.4099
Max Act: 6.0661. Min Act: -0.1700
Data Index: 6093143 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4099. Min Range: -6.4099
Max Act: 6.0974. Min Act: -0.1700
Data Index: 1035760 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4099. Min Range: -6.4099
Max Act: 6.0036. Min Act: -0.1700
Data Index: 3164978 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4099. Min Range: -6.4099
Max Act: 5.9724. Min Act: -0.1700
Data Index: 1505815 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4099. Min Range: -6.4099
Max Act: 6.0036. Min Act: -0.1700
Data Index: 4807969 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4099. Min Range: -6.4099
Max Act: 5.9724. Min Act: -0.1700
Data Index: 4371527 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4099. Min Range: -6.4099
Max Act: 5.9724. Min Act: -0.1700
Data Index: 3718660 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4099. Min Range: -6.4099
Max Act: 5.8786. Min Act: -0.1700
Data Index: 553004 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4099. Min Range: -6.4099
Max Act: 5.9099. Min Act: -0.1700
Data Index: 1221624 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4099. Min Range: -6.4099
Max Act: 5.8474. Min Act: -0.1700
Data Index: 3832430 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4099. Min Range: -6.4099
Max Act: 5.8474. Min Act: -0.1700
Data Index: 613475 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4099. Min Range: -6.4099
Max Act: 5.7849. Min Act: -0.1700
Data Index: 2123376 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4099. Min Range: -6.4099
Max Act: 5.8161. Min Act: -0.1700
Data Index: 4369640 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4099. Min Range: -6.4099
Max Act: 5.8161. Min Act: -0.1700
Data Index: 3947106 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19