Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2580 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.9808. Min Act: -0.1700
Data Index: 5236928 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.9183. Min Act: -0.1700
Data Index: 6575324 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.8870. Min Act: -0.1700
Data Index: 1033185 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.8870. Min Act: -0.1700
Data Index: 6353354 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.8245. Min Act: -0.1700
Data Index: 5686419 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.8558. Min Act: -0.1700
Data Index: 2967224 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.8558. Min Act: -0.1700
Data Index: 530337 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.8245. Min Act: -0.1700
Data Index: 3911068 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.8558. Min Act: -0.1700
Data Index: 3793611 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.8245. Min Act: -0.1700
Data Index: 5306473 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.8245. Min Act: -0.1700
Data Index: 6666448 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.7932. Min Act: -0.1700
Data Index: 4286338 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.8089. Min Act: -0.1700
Data Index: 290996 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.8558. Min Act: -0.1700
Data Index: 6914018 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.8089. Min Act: -0.1700
Data Index: 1178696 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.8245. Min Act: -0.1700
Data Index: 1218079 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.8089. Min Act: -0.1700
Data Index: 2147471 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.8089. Min Act: -0.1700
Data Index: 6499194 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.7932. Min Act: -0.1700
Data Index: 3882968 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9808. Min Range: -3.9808
Max Act: 3.8089. Min Act: -0.1700
Data Index: 5153191 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19