Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2656 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.5648. Min Act: -0.1700
Data Index: 798176 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.4398. Min Act: -0.1700
Data Index: 133093 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.4085. Min Act: -0.1700
Data Index: 4451666 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.4085. Min Act: -0.1700
Data Index: 7972726 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.3460. Min Act: -0.1700
Data Index: 133092 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.3460. Min Act: -0.1700
Data Index: 5522421 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.2835. Min Act: -0.1700
Data Index: 636341 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.2835. Min Act: -0.1700
Data Index: 4233435 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.2523. Min Act: -0.1700
Data Index: 464136 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.2523. Min Act: -0.1700
Data Index: 5605494 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.2835. Min Act: -0.1700
Data Index: 4209782 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.2835. Min Act: -0.1700
Data Index: 7212645 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.2210. Min Act: -0.1700
Data Index: 2103355 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.2523. Min Act: -0.1700
Data Index: 1038298 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.2210. Min Act: -0.1700
Data Index: 282651 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.2210. Min Act: -0.1700
Data Index: 381898 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.1273. Min Act: -0.1700
Data Index: 6401545 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.1585. Min Act: -0.1700
Data Index: 4772893 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.0960. Min Act: -0.1700
Data Index: 3490685 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5648. Min Range: -5.5648
Max Act: 5.0960. Min Act: -0.1700
Data Index: 3774861 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19