Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2850 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1107. Min Range: -6.1107
Max Act: 6.1107. Min Act: -0.1700
Data Index: 6616257 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.9545. Min Act: -0.1700
Data Index: 6237678 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.7670. Min Act: -0.1700
Data Index: 5564940 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.7982. Min Act: -0.1700
Data Index: 4553876 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.7357. Min Act: -0.1700
Data Index: 6616258 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.6732. Min Act: -0.1700
Data Index: 7363001 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.6420. Min Act: -0.1700
Data Index: 5757456 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.6420. Min Act: -0.1700
Data Index: 1301998 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.6107. Min Act: -0.1700
Data Index: 2075127 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.5795. Min Act: -0.1700
Data Index: 4908212 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.5482. Min Act: -0.1700
Data Index: 2580362 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.5482. Min Act: -0.1700
Data Index: 2501038 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.5482. Min Act: -0.1700
Data Index: 3585161 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.5482. Min Act: -0.1700
Data Index: 619020 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.5170. Min Act: -0.1700
Data Index: 406130 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.5170. Min Act: -0.1700
Data Index: 982852 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.5170. Min Act: -0.1700
Data Index: 5660033 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.4857. Min Act: -0.1700
Data Index: 7459706 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.4857. Min Act: -0.1700
Data Index: 3209879 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1107. Min Range: -6.1107
Max Act: 5.4857. Min Act: -0.1700
Data Index: 7118727 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19