Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2091 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1115. Min Range: -8.1115
Max Act: 8.1115. Min Act: -0.1700
Data Index: 1073313 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.9553. Min Act: -0.1700
Data Index: 1073316 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.9865. Min Act: -0.1700
Data Index: 1073314 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.9240. Min Act: -0.1700
Data Index: 1868426 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.6740. Min Act: -0.1700
Data Index: 6153356 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.4865. Min Act: -0.1700
Data Index: 5252652 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.3303. Min Act: -0.1700
Data Index: 4954504 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.3928. Min Act: -0.1700
Data Index: 4082325 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.2990. Min Act: -0.1700
Data Index: 4954514 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.2678. Min Act: -0.1700
Data Index: 4085911 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.3615. Min Act: -0.1700
Data Index: 5850157 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.3303. Min Act: -0.1700
Data Index: 301290 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.3615. Min Act: -0.1700
Data Index: 7421116 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.2990. Min Act: -0.1700
Data Index: 8059804 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.2678. Min Act: -0.1700
Data Index: 5168091 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.2053. Min Act: -0.1700
Data Index: 6399850 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.2365. Min Act: -0.1700
Data Index: 4205523 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.2990. Min Act: -0.1700
Data Index: 2487153 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.2990. Min Act: -0.1700
Data Index: 4896700 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1115. Min Range: -8.1115
Max Act: 7.2365. Min Act: -0.1700
Data Index: 169942 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19