Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3150 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0038. Min Range: -8.0038
Max Act: 8.0038. Min Act: -0.1700
Data Index: 2238883 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.8788. Min Act: -0.1700
Data Index: 5119949 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.8163. Min Act: -0.1700
Data Index: 2774322 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.8163. Min Act: -0.1700
Data Index: 3843632 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.7538. Min Act: -0.1700
Data Index: 7861118 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.6913. Min Act: -0.1700
Data Index: 7610553 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.6288. Min Act: -0.1700
Data Index: 4644211 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.6288. Min Act: -0.1700
Data Index: 6710676 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.5663. Min Act: -0.1700
Data Index: 6151004 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.5038. Min Act: -0.1700
Data Index: 286865 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.4100. Min Act: -0.1700
Data Index: 8785668 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.3788. Min Act: -0.1700
Data Index: 3671856 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.3788. Min Act: -0.1700
Data Index: 1656919 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.3163. Min Act: -0.1700
Data Index: 3985334 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.2850. Min Act: -0.1700
Data Index: 48233 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.3163. Min Act: -0.1700
Data Index: 6313443 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.2538. Min Act: -0.1700
Data Index: 3210178 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.2538. Min Act: -0.1700
Data Index: 4500478 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.1913. Min Act: -0.1700
Data Index: 6959088 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0038. Min Range: -8.0038
Max Act: 7.1913. Min Act: -0.1700
Data Index: 7481357 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19