Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4390 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.4073. Min Act: -0.1700
Data Index: 3051148 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.4387. Min Act: -0.1700
Data Index: 3226102 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.2818. Min Act: -0.1700
Data Index: 4562217 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.2504. Min Act: -0.1700
Data Index: 1683155 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.2033. Min Act: -0.1700
Data Index: 7606488 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.2347. Min Act: -0.1700
Data Index: 3056017 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.1718. Min Act: -0.1700
Data Index: 7932836 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.1246. Min Act: -0.1700
Data Index: 1964177 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.1246. Min Act: -0.1700
Data Index: 3293359 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.1246. Min Act: -0.1700
Data Index: 7388375 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.1088. Min Act: -0.1700
Data Index: 1762534 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.1088. Min Act: -0.1700
Data Index: 891741 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.0931. Min Act: -0.1700
Data Index: 846861 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.0931. Min Act: -0.1700
Data Index: 6503711 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.0773. Min Act: -0.1700
Data Index: 5075340 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.0615. Min Act: -0.1700
Data Index: 3678177 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.0615. Min Act: -0.1700
Data Index: 5998288 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.0457. Min Act: -0.1700
Data Index: 2286301 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.0300. Min Act: -0.1700
Data Index: 2418706 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4387. Min Range: -3.4387
Max Act: 3.0615. Min Act: -0.1700
Data Index: 1145855 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19