Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2210 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.6869. Min Act: -0.1700
Data Index: 1312476 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5306. Min Act: -0.1700
Data Index: 5248162 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5619. Min Act: -0.1700
Data Index: 5940432 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5619. Min Act: -0.1700
Data Index: 7768008 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5306. Min Act: -0.1700
Data Index: 8471451 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5306. Min Act: -0.1700
Data Index: 6063365 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5306. Min Act: -0.1700
Data Index: 4789099 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5619. Min Act: -0.1700
Data Index: 4069770 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5306. Min Act: -0.1700
Data Index: 4754738 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5306. Min Act: -0.1700
Data Index: 3578706 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.4994. Min Act: -0.1700
Data Index: 8292658 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5306. Min Act: -0.1700
Data Index: 2659203 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5306. Min Act: -0.1700
Data Index: 7744532 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.4994. Min Act: -0.1700
Data Index: 6591996 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.4994. Min Act: -0.1700
Data Index: 3746591 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.4681. Min Act: -0.1700
Data Index: 8600179 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.4994. Min Act: -0.1700
Data Index: 7488945 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.4994. Min Act: -0.1700
Data Index: 7497444 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5306. Min Act: -0.1700
Data Index: 2502898 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.4994. Min Act: -0.1700
Data Index: 6646446 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19