Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 827 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.6700. Min Act: -0.1700
Data Index: 5101063 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.5762. Min Act: -0.1700
Data Index: 6194367 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.5450. Min Act: -0.1700
Data Index: 7737635 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.5137. Min Act: -0.1700
Data Index: 2665505 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.4825. Min Act: -0.1700
Data Index: 2632095 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.4825. Min Act: -0.1700
Data Index: 8165622 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.4512. Min Act: -0.1700
Data Index: 7108192 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.4200. Min Act: -0.1700
Data Index: 1500023 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.4512. Min Act: -0.1700
Data Index: 1147102 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.4512. Min Act: -0.1700
Data Index: 199921 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.4200. Min Act: -0.1700
Data Index: 7642952 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.4200. Min Act: -0.1700
Data Index: 2377925 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.4200. Min Act: -0.1700
Data Index: 2915344 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.4200. Min Act: -0.1700
Data Index: 4652567 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.4200. Min Act: -0.1700
Data Index: 2907359 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.4200. Min Act: -0.1700
Data Index: 3761056 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.4200. Min Act: -0.1700
Data Index: 1605360 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.3887. Min Act: -0.1700
Data Index: 3940605 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.3887. Min Act: -0.1700
Data Index: 1820249 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6700. Min Range: -5.6700
Max Act: 5.3887. Min Act: -0.1700
Data Index: 4563532 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19