Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6223 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5585. Min Range: -7.5585
Max Act: 7.5585. Min Act: -0.1700
Data Index: 3307676 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5585. Min Range: -7.5585
Max Act: 7.3397. Min Act: -0.1700
Data Index: 5792425 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5585. Min Range: -7.5585
Max Act: 7.2772. Min Act: -0.1700
Data Index: 1130254 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5585. Min Range: -7.5585
Max Act: 7.2460. Min Act: -0.1700
Data Index: 1125504 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5585. Min Range: -7.5585
Max Act: 7.1522. Min Act: -0.1700
Data Index: 5643739 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5585. Min Range: -7.5585
Max Act: 7.0897. Min Act: -0.1700
Data Index: 4697904 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5585. Min Range: -7.5585
Max Act: 7.0897. Min Act: -0.1700
Data Index: 5294970 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5585. Min Range: -7.5585
Max Act: 6.9647. Min Act: -0.1700
Data Index: 7837257 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5585. Min Range: -7.5585
Max Act: 7.0272. Min Act: -0.1700
Data Index: 2958596 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5585. Min Range: -7.5585
Max Act: 6.9647. Min Act: -0.1700
Data Index: 2696008 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5585. Min Range: -7.5585
Max Act: 6.8710. Min Act: -0.1700
Data Index: 8189797 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5585. Min Range: -7.5585
Max Act: 6.9022. Min Act: -0.1700
Data Index: 8175273 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5585. Min Range: -7.5585
Max Act: 6.8397. Min Act: -0.1700
Data Index: 6507318 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5585. Min Range: -7.5585
Max Act: 6.8397. Min Act: -0.1700
Data Index: 5897716 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5585. Min Range: -7.5585
Max Act: 6.8397. Min Act: -0.1700
Data Index: 4986738 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5585. Min Range: -7.5585
Max Act: 6.8397. Min Act: -0.1700
Data Index: 4718201 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5585. Min Range: -7.5585
Max Act: 6.8397. Min Act: -0.1700
Data Index: 6994949 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5585. Min Range: -7.5585
Max Act: 6.8085. Min Act: -0.1700
Data Index: 8299524 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5585. Min Range: -7.5585
Max Act: 6.7772. Min Act: -0.1700
Data Index: 5739951 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5585. Min Range: -7.5585
Max Act: 6.7460. Min Act: -0.1700
Data Index: 6068905 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19