Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5356 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.5112. Min Act: -0.1700
Data Index: 7281615 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.5112. Min Act: -0.1700
Data Index: 2611948 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4798. Min Act: -0.1700
Data Index: 8131621 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4798. Min Act: -0.1700
Data Index: 6998854 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4798. Min Act: -0.1700
Data Index: 2562310 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4798. Min Act: -0.1700
Data Index: 148495 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4485. Min Act: -0.1700
Data Index: 2102054 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4485. Min Act: -0.1700
Data Index: 6399873 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4485. Min Act: -0.1700
Data Index: 7707795 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4171. Min Act: -0.1700
Data Index: 2523032 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4171. Min Act: -0.1700
Data Index: 6390498 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4171. Min Act: -0.1700
Data Index: 430632 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4171. Min Act: -0.1700
Data Index: 1165165 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4171. Min Act: -0.1700
Data Index: 63249 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4171. Min Act: -0.1700
Data Index: 2311087 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4171. Min Act: -0.1700
Data Index: 4173863 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4171. Min Act: -0.1700
Data Index: 244136 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4171. Min Act: -0.1700
Data Index: 6771795 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4171. Min Act: -0.1700
Data Index: 4989767 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5112. Min Range: -3.5112
Max Act: 3.4171. Min Act: -0.1700
Data Index: 6333399 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19