Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1526 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0982. Min Range: -4.0982
Max Act: 4.0982. Min Act: -0.1700
Data Index: 7243464 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.9732. Min Act: -0.1700
Data Index: 8349260 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.9419. Min Act: -0.1700
Data Index: 2064662 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.8637. Min Act: -0.1700
Data Index: 4236930 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.8168. Min Act: -0.1700
Data Index: 4738279 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.8168. Min Act: -0.1700
Data Index: 5032415 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.8168. Min Act: -0.1700
Data Index: 5287114 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.8012. Min Act: -0.1700
Data Index: 5940859 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.7855. Min Act: -0.1700
Data Index: 1629314 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.8012. Min Act: -0.1700
Data Index: 5159823 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.7855. Min Act: -0.1700
Data Index: 1157188 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.7699. Min Act: -0.1700
Data Index: 5276310 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.7699. Min Act: -0.1700
Data Index: 875811 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.7855. Min Act: -0.1700
Data Index: 6331400 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.7699. Min Act: -0.1700
Data Index: 5689318 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.7543. Min Act: -0.1700
Data Index: 1891328 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.7543. Min Act: -0.1700
Data Index: 4645055 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.7543. Min Act: -0.1700
Data Index: 4736964 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.7543. Min Act: -0.1700
Data Index: 5126138 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0982. Min Range: -4.0982
Max Act: 3.7543. Min Act: -0.1700
Data Index: 1985467 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19