Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 802 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4847. Min Range: -5.4847
Max Act: 5.4847. Min Act: -0.1700
Data Index: 3145823 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4847. Min Range: -5.4847
Max Act: 5.2035. Min Act: -0.1700
Data Index: 1525203 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4847. Min Range: -5.4847
Max Act: 5.1410. Min Act: -0.1700
Data Index: 6937779 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4847. Min Range: -5.4847
Max Act: 5.0785. Min Act: -0.1700
Data Index: 7781607 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4847. Min Range: -5.4847
Max Act: 5.0472. Min Act: -0.1700
Data Index: 2860533 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4847. Min Range: -5.4847
Max Act: 5.0785. Min Act: -0.1700
Data Index: 8577458 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4847. Min Range: -5.4847
Max Act: 5.0785. Min Act: -0.1700
Data Index: 4828552 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4847. Min Range: -5.4847
Max Act: 5.0160. Min Act: -0.1700
Data Index: 161641 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4847. Min Range: -5.4847
Max Act: 5.0785. Min Act: -0.1700
Data Index: 5924714 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4847. Min Range: -5.4847
Max Act: 5.0472. Min Act: -0.1700
Data Index: 7929255 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4847. Min Range: -5.4847
Max Act: 5.0472. Min Act: -0.1700
Data Index: 6789056 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4847. Min Range: -5.4847
Max Act: 5.0160. Min Act: -0.1700
Data Index: 5570432 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4847. Min Range: -5.4847
Max Act: 5.0472. Min Act: -0.1700
Data Index: 564928 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4847. Min Range: -5.4847
Max Act: 5.0160. Min Act: -0.1700
Data Index: 5467123 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4847. Min Range: -5.4847
Max Act: 5.0160. Min Act: -0.1700
Data Index: 1847026 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4847. Min Range: -5.4847
Max Act: 5.0160. Min Act: -0.1700
Data Index: 6489568 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4847. Min Range: -5.4847
Max Act: 4.9847. Min Act: -0.1700
Data Index: 263910 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4847. Min Range: -5.4847
Max Act: 4.9847. Min Act: -0.1700
Data Index: 6089244 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4847. Min Range: -5.4847
Max Act: 4.9847. Min Act: -0.1700
Data Index: 132876 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4847. Min Range: -5.4847
Max Act: 4.9847. Min Act: -0.1700
Data Index: 7086333 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19