Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3392 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.4411. Min Act: -0.1700
Data Index: 4414542 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.4097. Min Act: -0.1700
Data Index: 2512651 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.3940. Min Act: -0.1700
Data Index: 2433209 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.3470. Min Act: -0.1700
Data Index: 6761957 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.2685. Min Act: -0.1700
Data Index: 5862140 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.2371. Min Act: -0.1700
Data Index: 405602 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.2214. Min Act: -0.1700
Data Index: 1711092 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.2371. Min Act: -0.1700
Data Index: 4028656 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.2371. Min Act: -0.1700
Data Index: 6283933 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.2214. Min Act: -0.1700
Data Index: 2198058 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.2214. Min Act: -0.1700
Data Index: 382363 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.2056. Min Act: -0.1700
Data Index: 4362401 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.2056. Min Act: -0.1700
Data Index: 3041953 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.1899. Min Act: -0.1700
Data Index: 7900227 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.1742. Min Act: -0.1700
Data Index: 7907279 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.2056. Min Act: -0.1700
Data Index: 2129041 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.2056. Min Act: -0.1700
Data Index: 2492000 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.1899. Min Act: -0.1700
Data Index: 6860817 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.1742. Min Act: -0.1700
Data Index: 762018 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4411. Min Range: -3.4411
Max Act: 3.1742. Min Act: -0.1700
Data Index: 5903123 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19