Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3610 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.8133. Min Act: -0.1700
Data Index: 2662297 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.7195. Min Act: -0.1700
Data Index: 3074969 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.6725. Min Act: -0.1700
Data Index: 289540 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.6882. Min Act: -0.1700
Data Index: 5678608 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.6412. Min Act: -0.1700
Data Index: 6230954 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.6256. Min Act: -0.1700
Data Index: 5462175 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.6256. Min Act: -0.1700
Data Index: 802061 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.6099. Min Act: -0.1700
Data Index: 5470706 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.5943. Min Act: -0.1700
Data Index: 6097198 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.5943. Min Act: -0.1700
Data Index: 5823485 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.5943. Min Act: -0.1700
Data Index: 8190004 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.5786. Min Act: -0.1700
Data Index: 7125204 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.5786. Min Act: -0.1700
Data Index: 5470705 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.5786. Min Act: -0.1700
Data Index: 4925498 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.5473. Min Act: -0.1700
Data Index: 4318844 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.5630. Min Act: -0.1700
Data Index: 697448 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.5630. Min Act: -0.1700
Data Index: 5488075 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.5473. Min Act: -0.1700
Data Index: 3216773 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.5473. Min Act: -0.1700
Data Index: 4214554 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8133. Min Range: -3.8133
Max Act: 3.5317. Min Act: -0.1700
Data Index: 2006594 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19