Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4306 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.4830. Min Act: -0.1700
Data Index: 1481431 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.4517. Min Act: -0.1700
Data Index: 3200913 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.3892. Min Act: -0.1700
Data Index: 1760010 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.3892. Min Act: -0.1700
Data Index: 1893592 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.3892. Min Act: -0.1700
Data Index: 2591772 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.3580. Min Act: -0.1700
Data Index: 7672653 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.3580. Min Act: -0.1700
Data Index: 6112072 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.3580. Min Act: -0.1700
Data Index: 7403605 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.3267. Min Act: -0.1700
Data Index: 1138687 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.2955. Min Act: -0.1700
Data Index: 7944289 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.2955. Min Act: -0.1700
Data Index: 1033748 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.3267. Min Act: -0.1699
Data Index: 5298372 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.2330. Min Act: -0.1700
Data Index: 8260534 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.2642. Min Act: -0.1700
Data Index: 4923449 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.2642. Min Act: -0.1700
Data Index: 3566573 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.2330. Min Act: -0.1700
Data Index: 2744399 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.2330. Min Act: -0.1700
Data Index: 87208 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.2017. Min Act: -0.1700
Data Index: 3419742 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.2330. Min Act: -0.1700
Data Index: 722885 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4830. Min Range: -5.4830
Max Act: 5.2330. Min Act: -0.1700
Data Index: 382104 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19