Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2383 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0715. Min Range: -3.0715
Max Act: 3.0715. Min Act: -0.1700
Data Index: 5148275 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0715. Min Range: -3.0715
Max Act: 3.0084. Min Act: -0.1700
Data Index: 1839370 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.8659. Min Act: -0.1700
Data Index: 7086789 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.8341. Min Act: -0.1700
Data Index: 7123187 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.8659. Min Act: -0.1700
Data Index: 757451 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.8500. Min Act: -0.1700
Data Index: 7902840 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.8182. Min Act: -0.1700
Data Index: 6394522 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.8182. Min Act: -0.1700
Data Index: 8632944 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.8341. Min Act: -0.1700
Data Index: 4462500 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.8023. Min Act: -0.1700
Data Index: 6439536 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.7863. Min Act: -0.1700
Data Index: 2165584 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.7863. Min Act: -0.1700
Data Index: 7527295 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.7544. Min Act: -0.1700
Data Index: 5545177 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.7385. Min Act: -0.1700
Data Index: 6080496 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.7225. Min Act: -0.1700
Data Index: 1531593 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.7385. Min Act: -0.1700
Data Index: 8242412 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.7385. Min Act: -0.1700
Data Index: 7926767 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.7225. Min Act: -0.1700
Data Index: 5162040 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.7225. Min Act: -0.1700
Data Index: 2577671 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0715. Min Range: -3.0715
Max Act: 2.7385. Min Act: -0.1700
Data Index: 4075791 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19