Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5271. Min Range: -5.5271
Max Act: 5.5271. Min Act: -0.1700
Data Index: 6151328 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5271. Min Range: -5.5271
Max Act: 5.4021. Min Act: -0.1700
Data Index: 7729407 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5271. Min Range: -5.5271
Max Act: 5.3084. Min Act: -0.1700
Data Index: 4102454 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5271. Min Range: -5.5271
Max Act: 5.2771. Min Act: -0.1700
Data Index: 2953083 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5271. Min Range: -5.5271
Max Act: 5.1209. Min Act: -0.1700
Data Index: 2999423 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5271. Min Range: -5.5271
Max Act: 5.1209. Min Act: -0.1700
Data Index: 2647211 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5271. Min Range: -5.5271
Max Act: 5.0584. Min Act: -0.1700
Data Index: 1357332 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5271. Min Range: -5.5271
Max Act: 5.0896. Min Act: -0.1700
Data Index: 8385242 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5271. Min Range: -5.5271
Max Act: 5.0584. Min Act: -0.1700
Data Index: 5818378 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5271. Min Range: -5.5271
Max Act: 5.0584. Min Act: -0.1700
Data Index: 5820389 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5271. Min Range: -5.5271
Max Act: 5.0584. Min Act: -0.1700
Data Index: 7532310 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5271. Min Range: -5.5271
Max Act: 5.0271. Min Act: -0.1700
Data Index: 597119 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5271. Min Range: -5.5271
Max Act: 4.9959. Min Act: -0.1700
Data Index: 4189655 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5271. Min Range: -5.5271
Max Act: 4.9959. Min Act: -0.1700
Data Index: 8152964 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5271. Min Range: -5.5271
Max Act: 4.9959. Min Act: -0.1700
Data Index: 592808 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5271. Min Range: -5.5271
Max Act: 4.9959. Min Act: -0.1700
Data Index: 3650759 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5271. Min Range: -5.5271
Max Act: 4.9959. Min Act: -0.1700
Data Index: 1424960 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5271. Min Range: -5.5271
Max Act: 4.9646. Min Act: -0.1700
Data Index: 4774740 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5271. Min Range: -5.5271
Max Act: 4.9334. Min Act: -0.1700
Data Index: 5312766 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5271. Min Range: -5.5271
Max Act: 4.9334. Min Act: -0.1700
Data Index: 4682641 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19