Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3070 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.9151. Min Act: -0.1700
Data Index: 753618 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.8526. Min Act: -0.1700
Data Index: 8114594 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.8526. Min Act: -0.1700
Data Index: 121282 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.8526. Min Act: -0.1700
Data Index: 8808633 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.8213. Min Act: -0.1700
Data Index: 3347155 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.8213. Min Act: -0.1700
Data Index: 1095443 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.8213. Min Act: -0.1700
Data Index: 487372 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.8526. Min Act: -0.1700
Data Index: 992244 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.8213. Min Act: -0.1700
Data Index: 7415283 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.8213. Min Act: -0.1700
Data Index: 8657042 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.8213. Min Act: -0.1700
Data Index: 5584223 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.8213. Min Act: -0.1700
Data Index: 5045287 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.8213. Min Act: -0.1700
Data Index: 2737508 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.7900. Min Act: -0.1700
Data Index: 5903217 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.7900. Min Act: -0.1700
Data Index: 6818352 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.7588. Min Act: -0.1700
Data Index: 2140377 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.7900. Min Act: -0.1700
Data Index: 7693616 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.7900. Min Act: -0.1700
Data Index: 2257953 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.7900. Min Act: -0.1700
Data Index: 8043540 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9151. Min Range: -3.9151
Max Act: 3.7900. Min Act: -0.1700
Data Index: 2562770 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19