Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 758 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.8896. Min Act: -0.1700
Data Index: 7191357 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.7646. Min Act: -0.1700
Data Index: 680894 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.7334. Min Act: -0.1700
Data Index: 308644 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.6709. Min Act: -0.1700
Data Index: 5301516 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.7021. Min Act: -0.1700
Data Index: 8016642 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.7334. Min Act: -0.1700
Data Index: 6027087 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.7021. Min Act: -0.1700
Data Index: 5798398 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.7021. Min Act: -0.1700
Data Index: 1407606 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.6709. Min Act: -0.1700
Data Index: 6945209 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.6709. Min Act: -0.1700
Data Index: 3262257 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.7021. Min Act: -0.1700
Data Index: 7478436 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.6396. Min Act: -0.1700
Data Index: 1259754 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.6396. Min Act: -0.1700
Data Index: 4093738 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.6396. Min Act: -0.1700
Data Index: 6649138 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.6084. Min Act: -0.1700
Data Index: 288024 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.6084. Min Act: -0.1700
Data Index: 7922105 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.6084. Min Act: -0.1700
Data Index: 1382085 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.5771. Min Act: -0.1700
Data Index: 7627867 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.6084. Min Act: -0.1700
Data Index: 199619 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8896. Min Range: -5.8896
Max Act: 5.5459. Min Act: -0.1700
Data Index: 2019255 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19