Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2800 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0940. Min Range: -2.0940
Max Act: 2.0940. Min Act: -0.1700
Data Index: 2340375 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0940. Min Range: -2.0940
Max Act: 2.0773. Min Act: -0.1700
Data Index: 4151012 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0940. Min Range: -2.0940
Max Act: 2.0605. Min Act: -0.1700
Data Index: 8604107 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0940. Min Range: -2.0940
Max Act: 2.0437. Min Act: -0.1700
Data Index: 5062962 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0940. Min Range: -2.0940
Max Act: 2.0437. Min Act: -0.1700
Data Index: 1314107 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0940. Min Range: -2.0940
Max Act: 2.0437. Min Act: -0.1700
Data Index: 7808438 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0940. Min Range: -2.0940
Max Act: 2.0268. Min Act: -0.1699
Data Index: 74798 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0940. Min Range: -2.0940
Max Act: 2.0268. Min Act: -0.1700
Data Index: 487182 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0940. Min Range: -2.0940
Max Act: 2.0099. Min Act: -0.1700
Data Index: 5694165 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0940. Min Range: -2.0940
Max Act: 2.0099. Min Act: -0.1700
Data Index: 8818829 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0940. Min Range: -2.0940
Max Act: 2.0099. Min Act: -0.1700
Data Index: 3745188 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0940. Min Range: -2.0940
Max Act: 1.9930. Min Act: -0.1700
Data Index: 7492388 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0940. Min Range: -2.0940
Max Act: 1.9761. Min Act: -0.1700
Data Index: 5597716 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0940. Min Range: -2.0940
Max Act: 1.9592. Min Act: -0.1700
Data Index: 3248021 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0940. Min Range: -2.0940
Max Act: 1.9761. Min Act: -0.1700
Data Index: 7772114 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0940. Min Range: -2.0940
Max Act: 1.9761. Min Act: -0.1700
Data Index: 958506 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0940. Min Range: -2.0940
Max Act: 1.9761. Min Act: -0.1700
Data Index: 1678177 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0940. Min Range: -2.0940
Max Act: 1.9930. Min Act: -0.1700
Data Index: 2933174 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0940. Min Range: -2.0940
Max Act: 1.9592. Min Act: -0.1700
Data Index: 3909560 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0940. Min Range: -2.0940
Max Act: 1.9761. Min Act: -0.1700
Data Index: 3452744 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19