Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3310 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1082. Min Range: -7.1082
Max Act: 7.1082. Min Act: -0.1700
Data Index: 8248115 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.8582. Min Act: -0.1700
Data Index: 905315 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.8582. Min Act: -0.1700
Data Index: 753680 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.7957. Min Act: -0.1700
Data Index: 8312633 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.7957. Min Act: -0.1700
Data Index: 8070720 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.7332. Min Act: -0.1700
Data Index: 116609 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.7019. Min Act: -0.1700
Data Index: 3954039 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.7332. Min Act: -0.1700
Data Index: 561886 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.7957. Min Act: -0.1700
Data Index: 5721446 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.7332. Min Act: -0.1700
Data Index: 3531537 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.7332. Min Act: -0.1700
Data Index: 4655406 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.6707. Min Act: -0.1700
Data Index: 3954042 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.7019. Min Act: -0.1700
Data Index: 2085779 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.7019. Min Act: -0.1700
Data Index: 2867543 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.6394. Min Act: -0.1700
Data Index: 3989355 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.6082. Min Act: -0.1700
Data Index: 4342007 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.6082. Min Act: -0.1700
Data Index: 1432670 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.6082. Min Act: -0.1700
Data Index: 5330191 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.5769. Min Act: -0.1700
Data Index: 4359305 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1082. Min Range: -7.1082
Max Act: 6.5769. Min Act: -0.1700
Data Index: 974390 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19