Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3533 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.5049. Min Act: -0.1700
Data Index: 6614051 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.4736. Min Act: -0.1699
Data Index: 3677147 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.4111. Min Act: -0.1689
Data Index: 789419 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.2861. Min Act: -0.1700
Data Index: 3593415 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.3174. Min Act: -0.1700
Data Index: 4454259 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.1924. Min Act: -0.1700
Data Index: 6830315 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.1611. Min Act: -0.1700
Data Index: 1364650 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.1924. Min Act: -0.1700
Data Index: 1158359 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.1299. Min Act: -0.1697
Data Index: 4991983 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.0986. Min Act: -0.1700
Data Index: 6124542 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.0674. Min Act: -0.1700
Data Index: 4924958 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.0674. Min Act: -0.1700
Data Index: 8120212 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.0986. Min Act: -0.1700
Data Index: 304775 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.0674. Min Act: -0.1687
Data Index: 657470 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.0361. Min Act: -0.1700
Data Index: 2491084 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.0049. Min Act: -0.1696
Data Index: 7536879 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.0049. Min Act: -0.1682
Data Index: 8096377 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.0049. Min Act: -0.1700
Data Index: 7397301 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.0049. Min Act: -0.1700
Data Index: 4073025 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5049. Min Range: -5.5049
Max Act: 5.0049. Min Act: -0.1700
Data Index: 4688608 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19