Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.9283. Min Act: -0.1700
Data Index: 652800 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.8345. Min Act: -0.1700
Data Index: 4577218 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.7719. Min Act: -0.1700
Data Index: 4552074 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.7250. Min Act: -0.1700
Data Index: 1870903 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.7093. Min Act: -0.1700
Data Index: 8560666 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.6624. Min Act: -0.1700
Data Index: 7933085 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.6624. Min Act: -0.1700
Data Index: 2363225 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.5685. Min Act: -0.1700
Data Index: 7138664 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.5685. Min Act: -0.1700
Data Index: 415114 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.5529. Min Act: -0.1700
Data Index: 6182128 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.5372. Min Act: -0.1700
Data Index: 2115424 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.5372. Min Act: -0.1700
Data Index: 7375824 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.5059. Min Act: -0.1700
Data Index: 7970133 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.5215. Min Act: -0.1700
Data Index: 417972 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.5059. Min Act: -0.1700
Data Index: 7732989 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.5059. Min Act: -0.1700
Data Index: 3852482 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.5059. Min Act: -0.1700
Data Index: 7475719 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.5215. Min Act: -0.1700
Data Index: 2929546 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.4902. Min Act: -0.1700
Data Index: 2789216 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9283. Min Range: -3.9283
Max Act: 3.4902. Min Act: -0.1700
Data Index: 5476485 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19