Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 677 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1924. Min Range: -6.1924
Max Act: 6.1924. Min Act: -0.1700
Data Index: 3979440 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1924. Min Range: -6.1924
Max Act: 6.0362. Min Act: -0.1700
Data Index: 1242631 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1924. Min Range: -6.1924
Max Act: 6.0049. Min Act: -0.1700
Data Index: 3791505 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1924. Min Range: -6.1924
Max Act: 5.9737. Min Act: -0.1700
Data Index: 3387569 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1924. Min Range: -6.1924
Max Act: 5.9737. Min Act: -0.1700
Data Index: 7294860 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1924. Min Range: -6.1924
Max Act: 5.9737. Min Act: -0.1700
Data Index: 6095119 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1924. Min Range: -6.1924
Max Act: 5.9737. Min Act: -0.1700
Data Index: 3881172 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1924. Min Range: -6.1924
Max Act: 5.9424. Min Act: -0.1700
Data Index: 5649514 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1924. Min Range: -6.1924
Max Act: 5.9424. Min Act: -0.1700
Data Index: 7010958 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1924. Min Range: -6.1924
Max Act: 5.9112. Min Act: -0.1700
Data Index: 6387763 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1924. Min Range: -6.1924
Max Act: 5.9112. Min Act: -0.1700
Data Index: 7447078 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1924. Min Range: -6.1924
Max Act: 5.9424. Min Act: -0.1700
Data Index: 3474215 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1924. Min Range: -6.1924
Max Act: 5.9424. Min Act: -0.1700
Data Index: 587167 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1924. Min Range: -6.1924
Max Act: 5.9424. Min Act: -0.1700
Data Index: 3096282 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1924. Min Range: -6.1924
Max Act: 5.9424. Min Act: -0.1700
Data Index: 3559916 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1924. Min Range: -6.1924
Max Act: 5.9112. Min Act: -0.1700
Data Index: 3474213 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1924. Min Range: -6.1924
Max Act: 5.9112. Min Act: -0.1700
Data Index: 8707416 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1924. Min Range: -6.1924
Max Act: 5.9112. Min Act: -0.1700
Data Index: 5494474 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1924. Min Range: -6.1924
Max Act: 5.9112. Min Act: -0.1700
Data Index: 240110 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1924. Min Range: -6.1924
Max Act: 5.8799. Min Act: -0.1700
Data Index: 1896166 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19