Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5409 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.5775. Min Act: -0.1700
Data Index: 7504850 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.5150. Min Act: -0.1700
Data Index: 5048429 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.4525. Min Act: -0.1700
Data Index: 8697158 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.3900. Min Act: -0.1700
Data Index: 6500036 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.3275. Min Act: -0.1700
Data Index: 2394551 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.3275. Min Act: -0.1700
Data Index: 6239775 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.3275. Min Act: -0.1700
Data Index: 7344430 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.2650. Min Act: -0.1700
Data Index: 5013415 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.2650. Min Act: -0.1700
Data Index: 5799823 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.2650. Min Act: -0.1700
Data Index: 816894 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.2650. Min Act: -0.1700
Data Index: 153397 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.2025. Min Act: -0.1700
Data Index: 6960601 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.1400. Min Act: -0.1700
Data Index: 5585269 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.1400. Min Act: -0.1700
Data Index: 5389706 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.1400. Min Act: -0.1700
Data Index: 4636320 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.2025. Min Act: -0.1700
Data Index: 3653211 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.2025. Min Act: -0.1700
Data Index: 3020068 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.1400. Min Act: -0.1700
Data Index: 7025998 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.1400. Min Act: -0.1700
Data Index: 632746 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5775. Min Range: -8.5775
Max Act: 8.1400. Min Act: -0.1700
Data Index: 3741750 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19