Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4181 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7482. Min Range: -8.7482
Max Act: 8.7482. Min Act: -0.1700
Data Index: 4137133 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7482. Min Range: -8.7482
Max Act: 8.6857. Min Act: -0.1700
Data Index: 3326327 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7482. Min Range: -8.7482
Max Act: 8.5607. Min Act: -0.1700
Data Index: 957411 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7482. Min Range: -8.7482
Max Act: 8.5607. Min Act: -0.1700
Data Index: 5939993 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7482. Min Range: -8.7482
Max Act: 8.3732. Min Act: -0.1700
Data Index: 8074466 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7482. Min Range: -8.7482
Max Act: 8.3107. Min Act: -0.1700
Data Index: 6899440 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7482. Min Range: -8.7482
Max Act: 8.2482. Min Act: -0.1700
Data Index: 1485028 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7482. Min Range: -8.7482
Max Act: 8.1232. Min Act: -0.1700
Data Index: 4804632 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7482. Min Range: -8.7482
Max Act: 8.1232. Min Act: -0.1700
Data Index: 4835196 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7482. Min Range: -8.7482
Max Act: 7.9357. Min Act: -0.1700
Data Index: 4243388 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7482. Min Range: -8.7482
Max Act: 7.9357. Min Act: -0.1700
Data Index: 3539838 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7482. Min Range: -8.7482
Max Act: 7.8107. Min Act: -0.1700
Data Index: 38073 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7482. Min Range: -8.7482
Max Act: 7.6857. Min Act: -0.1700
Data Index: 1356620 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7482. Min Range: -8.7482
Max Act: 7.6232. Min Act: -0.1700
Data Index: 1416784 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7482. Min Range: -8.7482
Max Act: 7.5920. Min Act: -0.1700
Data Index: 4191495 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7482. Min Range: -8.7482
Max Act: 7.5607. Min Act: -0.1700
Data Index: 3679148 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7482. Min Range: -8.7482
Max Act: 7.5295. Min Act: -0.1700
Data Index: 1928758 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7482. Min Range: -8.7482
Max Act: 7.5295. Min Act: -0.1700
Data Index: 3252185 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7482. Min Range: -8.7482
Max Act: 7.5295. Min Act: -0.1700
Data Index: 8342127 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7482. Min Range: -8.7482
Max Act: 7.4982. Min Act: -0.1700
Data Index: 1763377 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19