Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2473 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.6952. Min Act: -0.1700
Data Index: 5597219 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.6639. Min Act: -0.1700
Data Index: 2762768 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.5702. Min Act: -0.1700
Data Index: 3869501 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.5077. Min Act: -0.1700
Data Index: 5989305 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.5389. Min Act: -0.1700
Data Index: 8051454 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.5077. Min Act: -0.1700
Data Index: 4318244 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.5077. Min Act: -0.1700
Data Index: 3832464 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.5077. Min Act: -0.1700
Data Index: 5759998 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.5077. Min Act: -0.1700
Data Index: 4211701 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.4452. Min Act: -0.1700
Data Index: 8491040 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.5077. Min Act: -0.1700
Data Index: 952036 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.5077. Min Act: -0.1700
Data Index: 3886844 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.4764. Min Act: -0.1700
Data Index: 8109543 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.4452. Min Act: -0.1700
Data Index: 3044448 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.5077. Min Act: -0.1700
Data Index: 684491 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.4764. Min Act: -0.1700
Data Index: 2875543 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.3827. Min Act: -0.1700
Data Index: 6166385 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.4764. Min Act: -0.1700
Data Index: 4582058 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.4139. Min Act: -0.1700
Data Index: 5047305 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6952. Min Range: -5.6952
Max Act: 5.4764. Min Act: -0.1700
Data Index: 2598365 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19