Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5420 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2660. Min Act: -0.1700
Data Index: 5831692 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2972. Min Act: -0.1700
Data Index: 5392718 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2660. Min Act: -0.1700
Data Index: 334080 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2660. Min Act: -0.1700
Data Index: 4906211 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2660. Min Act: -0.1700
Data Index: 3520351 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2660. Min Act: -0.1700
Data Index: 4631678 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2660. Min Act: -0.1700
Data Index: 4175122 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2660. Min Act: -0.1700
Data Index: 8095750 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2972. Min Act: -0.1700
Data Index: 7358884 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2660. Min Act: -0.1700
Data Index: 2409573 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2660. Min Act: -0.1700
Data Index: 7118138 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2972. Min Act: -0.1700
Data Index: 5915056 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2660. Min Act: -0.1700
Data Index: 3310932 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2660. Min Act: -0.1698
Data Index: 1459820 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2660. Min Act: -0.1700
Data Index: 1383928 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2660. Min Act: -0.1700
Data Index: 3709420 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2660. Min Act: -0.1700
Data Index: 3857826 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2660. Min Act: -0.1700
Data Index: 2623477 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2347. Min Act: -0.1700
Data Index: 2060797 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2972. Min Range: -4.2972
Max Act: 4.2347. Min Act: -0.1700
Data Index: 3187107 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19