Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 222 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5311. Min Range: -9.5311
Max Act: 9.5311. Min Act: -0.1700
Data Index: 554016 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5311. Min Range: -9.5311
Max Act: 9.3436. Min Act: -0.1700
Data Index: 3503104 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5311. Min Range: -9.5311
Max Act: 9.2186. Min Act: -0.1700
Data Index: 2729794 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5311. Min Range: -9.5311
Max Act: 9.1561. Min Act: -0.1700
Data Index: 7334606 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5311. Min Range: -9.5311
Max Act: 9.0936. Min Act: -0.1700
Data Index: 258626 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5311. Min Range: -9.5311
Max Act: 9.0311. Min Act: -0.1700
Data Index: 7576392 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5311. Min Range: -9.5311
Max Act: 9.0311. Min Act: -0.1700
Data Index: 3692663 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5311. Min Range: -9.5311
Max Act: 8.9686. Min Act: -0.1700
Data Index: 7836809 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5311. Min Range: -9.5311
Max Act: 8.9686. Min Act: -0.1700
Data Index: 2373159 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5311. Min Range: -9.5311
Max Act: 8.9061. Min Act: -0.1700
Data Index: 445514 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5311. Min Range: -9.5311
Max Act: 8.9061. Min Act: -0.1700
Data Index: 5301813 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5311. Min Range: -9.5311
Max Act: 8.9061. Min Act: -0.1700
Data Index: 7615305 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5311. Min Range: -9.5311
Max Act: 8.9061. Min Act: -0.1700
Data Index: 5652753 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5311. Min Range: -9.5311
Max Act: 8.8436. Min Act: -0.1700
Data Index: 6441420 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5311. Min Range: -9.5311
Max Act: 8.8436. Min Act: -0.1700
Data Index: 188490 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5311. Min Range: -9.5311
Max Act: 8.8436. Min Act: -0.1700
Data Index: 4874000 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5311. Min Range: -9.5311
Max Act: 8.8436. Min Act: -0.1700
Data Index: 8258593 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5311. Min Range: -9.5311
Max Act: 8.7811. Min Act: -0.1700
Data Index: 833856 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5311. Min Range: -9.5311
Max Act: 8.7811. Min Act: -0.1700
Data Index: 1453812 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5311. Min Range: -9.5311
Max Act: 8.7811. Min Act: -0.1700
Data Index: 858830 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19