Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4223 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2576. Min Range: -5.2576
Max Act: 5.2576. Min Act: -0.1700
Data Index: 555846 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2576. Min Range: -5.2576
Max Act: 5.0701. Min Act: -0.1700
Data Index: 294993 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2576. Min Range: -5.2576
Max Act: 5.0701. Min Act: -0.1700
Data Index: 161394 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2576. Min Range: -5.2576
Max Act: 5.0389. Min Act: -0.1700
Data Index: 1552349 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2576. Min Range: -5.2576
Max Act: 5.0389. Min Act: -0.1700
Data Index: 1576001 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2576. Min Range: -5.2576
Max Act: 5.0389. Min Act: -0.1700
Data Index: 2037603 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2576. Min Range: -5.2576
Max Act: 5.0076. Min Act: -0.1700
Data Index: 3774623 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2576. Min Range: -5.2576
Max Act: 5.0076. Min Act: -0.1700
Data Index: 7247414 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2576. Min Range: -5.2576
Max Act: 4.9764. Min Act: -0.1700
Data Index: 1978388 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2576. Min Range: -5.2576
Max Act: 4.9764. Min Act: -0.1700
Data Index: 158421 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2576. Min Range: -5.2576
Max Act: 5.0076. Min Act: -0.1700
Data Index: 7971858 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2576. Min Range: -5.2576
Max Act: 4.9764. Min Act: -0.1700
Data Index: 8806843 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2576. Min Range: -5.2576
Max Act: 4.9451. Min Act: -0.1700
Data Index: 7484071 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2576. Min Range: -5.2576
Max Act: 4.9764. Min Act: -0.1700
Data Index: 7274200 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2576. Min Range: -5.2576
Max Act: 4.9764. Min Act: -0.1700
Data Index: 4643174 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2576. Min Range: -5.2576
Max Act: 4.9451. Min Act: -0.1700
Data Index: 7077193 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2576. Min Range: -5.2576
Max Act: 4.9451. Min Act: -0.1700
Data Index: 4901323 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2576. Min Range: -5.2576
Max Act: 4.9451. Min Act: -0.1700
Data Index: 5452638 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2576. Min Range: -5.2576
Max Act: 4.9139. Min Act: -0.1700
Data Index: 8099127 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2576. Min Range: -5.2576
Max Act: 4.9139. Min Act: -0.1700
Data Index: 2092799 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19