Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 617 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.6997. Min Act: -0.1700
Data Index: 4600810 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.5747. Min Act: -0.1700
Data Index: 3614982 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.5434. Min Act: -0.1700
Data Index: 7782734 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.5434. Min Act: -0.1700
Data Index: 3112154 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.5122. Min Act: -0.1700
Data Index: 385643 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.4809. Min Act: -0.1700
Data Index: 4595237 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.4497. Min Act: -0.1700
Data Index: 7673581 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.4184. Min Act: -0.1700
Data Index: 5188136 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.3559. Min Act: -0.1700
Data Index: 679094 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.3559. Min Act: -0.1700
Data Index: 1885345 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.3559. Min Act: -0.1700
Data Index: 7389002 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.3559. Min Act: -0.1700
Data Index: 8589651 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.3559. Min Act: -0.1700
Data Index: 6877062 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.3559. Min Act: -0.1700
Data Index: 227919 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.3247. Min Act: -0.1700
Data Index: 2375123 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.3872. Min Act: -0.1700
Data Index: 4518474 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.3247. Min Act: -0.1700
Data Index: 2448960 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.3247. Min Act: -0.1700
Data Index: 966919 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.3559. Min Act: -0.1700
Data Index: 7470771 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6997. Min Range: -5.6997
Max Act: 5.3247. Min Act: -0.1700
Data Index: 7622004 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19