Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.9621. Min Act: -0.1700
Data Index: 8816058 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.9309. Min Act: -0.1700
Data Index: 6094574 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.8371. Min Act: -0.1700
Data Index: 6461743 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.8059. Min Act: -0.1700
Data Index: 8449270 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.7746. Min Act: -0.1700
Data Index: 7777369 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.7746. Min Act: -0.1700
Data Index: 688043 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.7434. Min Act: -0.1700
Data Index: 6190851 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.7434. Min Act: -0.1700
Data Index: 6223120 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.7434. Min Act: -0.1700
Data Index: 2962908 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.7121. Min Act: -0.1700
Data Index: 4297981 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.6809. Min Act: -0.1700
Data Index: 947289 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.6809. Min Act: -0.1700
Data Index: 3539123 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.6809. Min Act: -0.1700
Data Index: 3237206 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.6496. Min Act: -0.1700
Data Index: 3747481 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.6496. Min Act: -0.1700
Data Index: 5110161 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.6496. Min Act: -0.1700
Data Index: 3569702 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.6496. Min Act: -0.1700
Data Index: 6911456 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.6184. Min Act: -0.1700
Data Index: 4573508 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.5871. Min Act: -0.1700
Data Index: 5027315 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9621. Min Range: -4.9621
Max Act: 4.6496. Min Act: -0.1700
Data Index: 8433161 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19