Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.8663. Min Act: -0.1700
Data Index: 8141917 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.8663. Min Act: -0.1700
Data Index: 936881 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.8663. Min Act: -0.1700
Data Index: 6719316 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.8345. Min Act: -0.1700
Data Index: 3646359 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.8345. Min Act: -0.1700
Data Index: 4636400 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.7867. Min Act: -0.1700
Data Index: 1622250 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.8027. Min Act: -0.1700
Data Index: 8537612 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.8027. Min Act: -0.1700
Data Index: 293218 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.7867. Min Act: -0.1700
Data Index: 3791614 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.8027. Min Act: -0.1700
Data Index: 3948031 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.7867. Min Act: -0.1700
Data Index: 3777436 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.7867. Min Act: -0.1700
Data Index: 8197610 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.7867. Min Act: -0.1700
Data Index: 5576146 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.7867. Min Act: -0.1700
Data Index: 5366540 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.7708. Min Act: -0.1700
Data Index: 7554750 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.7867. Min Act: -0.1700
Data Index: 7313466 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.7867. Min Act: -0.1700
Data Index: 6999054 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.7867. Min Act: -0.1700
Data Index: 5920316 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.7708. Min Act: -0.1700
Data Index: 2996793 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8663. Min Range: -2.8663
Max Act: 2.7708. Min Act: -0.1700
Data Index: 5678691 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19