Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3867 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.4787. Min Act: -0.1700
Data Index: 6155812 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.4161. Min Act: -0.1700
Data Index: 4915096 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.4004. Min Act: -0.1700
Data Index: 1416620 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.3690. Min Act: -0.1700
Data Index: 7119090 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.3376. Min Act: -0.1700
Data Index: 8689228 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.3376. Min Act: -0.1700
Data Index: 640753 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.3063. Min Act: -0.1700
Data Index: 4360651 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.3063. Min Act: -0.1700
Data Index: 1816284 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.2906. Min Act: -0.1700
Data Index: 6857873 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.2749. Min Act: -0.1700
Data Index: 8492922 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.2591. Min Act: -0.1700
Data Index: 5200970 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.2749. Min Act: -0.1700
Data Index: 2121431 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.2906. Min Act: -0.1700
Data Index: 336060 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.2591. Min Act: -0.1700
Data Index: 1627114 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.2277. Min Act: -0.1700
Data Index: 2243902 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.2434. Min Act: -0.1700
Data Index: 4968387 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.2434. Min Act: -0.1700
Data Index: 1842525 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.2434. Min Act: -0.1700
Data Index: 4202903 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.2120. Min Act: -0.1700
Data Index: 750909 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4787. Min Range: -3.4787
Max Act: 3.2120. Min Act: -0.1700
Data Index: 112856 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19