Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.6100. Min Act: -0.1700
Data Index: 6028315 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.5630. Min Act: -0.1700
Data Index: 102120 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.5317. Min Act: -0.1700
Data Index: 4680556 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.5004. Min Act: -0.1700
Data Index: 4836102 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.5004. Min Act: -0.1700
Data Index: 2117380 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.4847. Min Act: -0.1700
Data Index: 8574598 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.4534. Min Act: -0.1700
Data Index: 5322334 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.4377. Min Act: -0.1700
Data Index: 7218358 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.4377. Min Act: -0.1700
Data Index: 5629234 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.4221. Min Act: -0.1700
Data Index: 3128889 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.4377. Min Act: -0.1700
Data Index: 6120232 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.4064. Min Act: -0.1700
Data Index: 4749287 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.4064. Min Act: -0.1700
Data Index: 2341533 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.3907. Min Act: -0.1700
Data Index: 2654098 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.4064. Min Act: -0.1700
Data Index: 5594983 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.4064. Min Act: -0.1700
Data Index: 7032202 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.3750. Min Act: -0.1700
Data Index: 4512769 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.3593. Min Act: -0.1700
Data Index: 1178263 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.3593. Min Act: -0.1700
Data Index: 1282583 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6100. Min Range: -3.6100
Max Act: 3.3593. Min Act: -0.1700
Data Index: 5117435 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19