Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3367 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.4569. Min Act: -0.1700
Data Index: 462751 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.2372. Min Act: -0.1700
Data Index: 184129 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.2215. Min Act: -0.1700
Data Index: 4953783 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.2058. Min Act: -0.1700
Data Index: 3382164 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.1743. Min Act: -0.1700
Data Index: 1102587 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.1586. Min Act: -0.1700
Data Index: 2105705 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.1271. Min Act: -0.1700
Data Index: 4578759 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.1271. Min Act: -0.1700
Data Index: 1873555 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.0956. Min Act: -0.1700
Data Index: 6586619 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.0956. Min Act: -0.1700
Data Index: 1307633 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.0798. Min Act: -0.1700
Data Index: 6721193 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.0798. Min Act: -0.1700
Data Index: 184128 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.0956. Min Act: -0.1700
Data Index: 7607211 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.0956. Min Act: -0.1700
Data Index: 4076279 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.0798. Min Act: -0.1700
Data Index: 6160410 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.0640. Min Act: -0.1700
Data Index: 2762544 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.0640. Min Act: -0.1700
Data Index: 6628690 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.0483. Min Act: -0.1700
Data Index: 5407864 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.0483. Min Act: -0.1700
Data Index: 6803598 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4569. Min Range: -3.4569
Max Act: 3.0167. Min Act: -0.1700
Data Index: 4822790 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19