Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3665 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7787. Min Act: -0.1685
Data Index: 8215022 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7873. Min Act: -0.1700
Data Index: 2544218 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7873. Min Act: -0.1700
Data Index: 732489 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7701. Min Act: -0.1699
Data Index: 6789459 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7701. Min Act: -0.1700
Data Index: 3500926 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7528. Min Act: -0.1699
Data Index: 3407420 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7528. Min Act: -0.1700
Data Index: 442494 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7528. Min Act: -0.1700
Data Index: 5293207 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7615. Min Act: -0.1700
Data Index: 4040059 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7528. Min Act: -0.1700
Data Index: 5925703 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7355. Min Act: -0.1700
Data Index: 5849585 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7442. Min Act: -0.1699
Data Index: 1874377 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7269. Min Act: -0.1700
Data Index: 7789597 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7355. Min Act: -0.1700
Data Index: 8724902 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7269. Min Act: -0.1699
Data Index: 8822720 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7355. Min Act: -0.1700
Data Index: 7917525 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7355. Min Act: -0.1700
Data Index: 2312129 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7269. Min Act: -0.1700
Data Index: 7382566 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7269. Min Act: -0.1700
Data Index: 1887825 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7873. Min Range: -1.7873
Max Act: 1.7269. Min Act: -0.1700
Data Index: 2888408 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19