Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2949. Min Range: -5.2949
Max Act: 5.2949. Min Act: -0.1700
Data Index: 553088 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2949. Min Range: -5.2949
Max Act: 5.2324. Min Act: -0.1700
Data Index: 906888 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2949. Min Range: -5.2949
Max Act: 5.0449. Min Act: -0.1700
Data Index: 2291997 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2949. Min Range: -5.2949
Max Act: 5.0449. Min Act: -0.1700
Data Index: 5057866 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2949. Min Range: -5.2949
Max Act: 5.0137. Min Act: -0.1700
Data Index: 7390600 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2949. Min Range: -5.2949
Max Act: 4.9824. Min Act: -0.1700
Data Index: 854429 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2949. Min Range: -5.2949
Max Act: 4.9512. Min Act: -0.1700
Data Index: 8577152 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2949. Min Range: -5.2949
Max Act: 4.9512. Min Act: -0.1700
Data Index: 8751099 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2949. Min Range: -5.2949
Max Act: 4.9824. Min Act: -0.1700
Data Index: 5057865 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2949. Min Range: -5.2949
Max Act: 4.9512. Min Act: -0.1700
Data Index: 5872195 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2949. Min Range: -5.2949
Max Act: 4.9512. Min Act: -0.1700
Data Index: 5057867 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2949. Min Range: -5.2949
Max Act: 4.9199. Min Act: -0.1700
Data Index: 2129984 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2949. Min Range: -5.2949
Max Act: 4.9199. Min Act: -0.1700
Data Index: 3698175 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2949. Min Range: -5.2949
Max Act: 4.9199. Min Act: -0.1700
Data Index: 3514550 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2949. Min Range: -5.2949
Max Act: 4.9512. Min Act: -0.1700
Data Index: 6495604 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2949. Min Range: -5.2949
Max Act: 4.9199. Min Act: -0.1700
Data Index: 6404339 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2949. Min Range: -5.2949
Max Act: 4.8887. Min Act: -0.1700
Data Index: 7047191 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2949. Min Range: -5.2949
Max Act: 4.8887. Min Act: -0.1700
Data Index: 753972 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2949. Min Range: -5.2949
Max Act: 4.8887. Min Act: -0.1700
Data Index: 2940096 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2949. Min Range: -5.2949
Max Act: 4.8887. Min Act: -0.1700
Data Index: 3053467 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19