Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3065 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.4038. Min Act: -0.1700
Data Index: 1463893 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.3413. Min Act: -0.1700
Data Index: 1810195 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.3413. Min Act: -0.1700
Data Index: 4123931 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.2476. Min Act: -0.1700
Data Index: 4636178 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.2163. Min Act: -0.1700
Data Index: 3987049 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.2163. Min Act: -0.1700
Data Index: 6506667 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.2163. Min Act: -0.1700
Data Index: 4422193 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.2163. Min Act: -0.1700
Data Index: 3728057 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.2163. Min Act: -0.1700
Data Index: 4468693 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.1851. Min Act: -0.1700
Data Index: 7313162 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.1538. Min Act: -0.1700
Data Index: 7780523 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.1226. Min Act: -0.1700
Data Index: 1610417 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.1226. Min Act: -0.1700
Data Index: 1413700 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.1226. Min Act: -0.1700
Data Index: 4173325 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.0913. Min Act: -0.1700
Data Index: 6643537 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.0913. Min Act: -0.1700
Data Index: 2096179 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.1226. Min Act: -0.1700
Data Index: 499555 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.0913. Min Act: -0.1700
Data Index: 1827026 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.0601. Min Act: -0.1700
Data Index: 827739 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.0601. Min Act: -0.1700
Data Index: 3945209 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19