Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 281 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.7651. Min Act: -0.1700
Data Index: 1999984 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.6556. Min Act: -0.1700
Data Index: 1133365 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.5304. Min Act: -0.1700
Data Index: 3705541 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.4364. Min Act: -0.1700
Data Index: 3827094 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.4207. Min Act: -0.1700
Data Index: 6879874 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.3423. Min Act: -0.1700
Data Index: 7777862 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.3266. Min Act: -0.1700
Data Index: 3196301 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.3109. Min Act: -0.1700
Data Index: 4908373 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.2952. Min Act: -0.1700
Data Index: 7538257 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.2795. Min Act: -0.1700
Data Index: 5238009 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.2638. Min Act: -0.1700
Data Index: 1775315 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.2638. Min Act: -0.1700
Data Index: 4513984 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.2481. Min Act: -0.1700
Data Index: 4761414 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.2481. Min Act: -0.1700
Data Index: 2788231 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.2324. Min Act: -0.1700
Data Index: 7623729 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.1852. Min Act: -0.1700
Data Index: 425721 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.2009. Min Act: -0.1700
Data Index: 7471046 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.1852. Min Act: -0.1700
Data Index: 2949592 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.1537. Min Act: -0.1700
Data Index: 778226 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7651. Min Range: -3.7651
Max Act: 3.1380. Min Act: -0.1700
Data Index: 6074797 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19