Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6278 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2767. Min Range: -7.2767
Max Act: 7.2767. Min Act: -0.1700
Data Index: 3380341 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.5580. Min Act: -0.1700
Data Index: 318063 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.5580. Min Act: -0.1700
Data Index: 1656637 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.5267. Min Act: -0.1700
Data Index: 7266976 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.4017. Min Act: -0.1700
Data Index: 4466377 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.3705. Min Act: -0.1700
Data Index: 4740331 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.3705. Min Act: -0.1700
Data Index: 2701608 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.3392. Min Act: -0.1700
Data Index: 2704219 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.3392. Min Act: -0.1700
Data Index: 8313282 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.3080. Min Act: -0.1700
Data Index: 8699682 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.3080. Min Act: -0.1700
Data Index: 5729278 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.3080. Min Act: -0.1700
Data Index: 4726544 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.2767. Min Act: -0.1700
Data Index: 3933563 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.2767. Min Act: -0.1700
Data Index: 1306466 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.3080. Min Act: -0.1700
Data Index: 2345352 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.2767. Min Act: -0.1700
Data Index: 3903276 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.2767. Min Act: -0.1700
Data Index: 3229675 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.2767. Min Act: -0.1700
Data Index: 2430105 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.2455. Min Act: -0.1700
Data Index: 5832122 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2767. Min Range: -7.2767
Max Act: 6.1830. Min Act: -0.1700
Data Index: 6727467 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19