Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5865 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.9994. Min Act: -0.1700
Data Index: 2750667 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.6869. Min Act: -0.1700
Data Index: 7109920 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.6869. Min Act: -0.1700
Data Index: 725617 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.6244. Min Act: -0.1700
Data Index: 6737504 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.5931. Min Act: -0.1700
Data Index: 4180835 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.5931. Min Act: -0.1700
Data Index: 3759216 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.5306. Min Act: -0.1700
Data Index: 6799495 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.4994. Min Act: -0.1700
Data Index: 2110722 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.4369. Min Act: -0.1700
Data Index: 2494235 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.4369. Min Act: -0.1700
Data Index: 8654672 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.4056. Min Act: -0.1700
Data Index: 4407667 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.4369. Min Act: -0.1700
Data Index: 2864068 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.3431. Min Act: -0.1700
Data Index: 8712095 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.3744. Min Act: -0.1700
Data Index: 7042826 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.3431. Min Act: -0.1700
Data Index: 4854238 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.3431. Min Act: -0.1700
Data Index: 3928711 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.3744. Min Act: -0.1700
Data Index: 4839839 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.3119. Min Act: -0.1700
Data Index: 5890342 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.3119. Min Act: -0.1700
Data Index: 3847193 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9994. Min Range: -7.9994
Max Act: 7.2181. Min Act: -0.1700
Data Index: 5280055 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19