Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1898 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5003. Min Range: -6.5003
Max Act: 6.5003. Min Act: -0.1700
Data Index: 876202 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5003. Min Range: -6.5003
Max Act: 6.4066. Min Act: -0.1700
Data Index: 3881534 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5003. Min Range: -6.5003
Max Act: 6.3128. Min Act: -0.1700
Data Index: 1104197 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5003. Min Range: -6.5003
Max Act: 6.1566. Min Act: -0.1700
Data Index: 3810438 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5003. Min Range: -6.5003
Max Act: 6.1566. Min Act: -0.1700
Data Index: 1145634 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5003. Min Range: -6.5003
Max Act: 6.1566. Min Act: -0.1700
Data Index: 5583311 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5003. Min Range: -6.5003
Max Act: 6.1253. Min Act: -0.1700
Data Index: 1465972 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5003. Min Range: -6.5003
Max Act: 6.1253. Min Act: -0.1700
Data Index: 2103461 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5003. Min Range: -6.5003
Max Act: 6.1566. Min Act: -0.1700
Data Index: 115882 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5003. Min Range: -6.5003
Max Act: 6.0941. Min Act: -0.1700
Data Index: 5553505 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5003. Min Range: -6.5003
Max Act: 6.0941. Min Act: -0.1700
Data Index: 1082549 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5003. Min Range: -6.5003
Max Act: 6.0628. Min Act: -0.1700
Data Index: 5148849 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5003. Min Range: -6.5003
Max Act: 6.0316. Min Act: -0.1700
Data Index: 2292025 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5003. Min Range: -6.5003
Max Act: 6.0003. Min Act: -0.1700
Data Index: 87216 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5003. Min Range: -6.5003
Max Act: 5.9378. Min Act: -0.1700
Data Index: 8186120 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5003. Min Range: -6.5003
Max Act: 5.9378. Min Act: -0.1700
Data Index: 6600997 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5003. Min Range: -6.5003
Max Act: 5.9691. Min Act: -0.1700
Data Index: 8781470 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5003. Min Range: -6.5003
Max Act: 5.9378. Min Act: -0.1700
Data Index: 8471716 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5003. Min Range: -6.5003
Max Act: 5.9066. Min Act: -0.1700
Data Index: 1488106 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5003. Min Range: -6.5003
Max Act: 5.9066. Min Act: -0.1700
Data Index: 221837 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19