Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2375 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1658. Min Range: -4.1658
Max Act: 4.1658. Min Act: -0.1700
Data Index: 8023565 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1658. Min Range: -4.1658
Max Act: 4.0720. Min Act: -0.1700
Data Index: 5336694 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1658. Min Range: -4.1658
Max Act: 4.0408. Min Act: -0.1700
Data Index: 7803843 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1658. Min Range: -4.1658
Max Act: 3.9782. Min Act: -0.1700
Data Index: 7803854 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1658. Min Range: -4.1658
Max Act: 4.0095. Min Act: -0.1698
Data Index: 5072173 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1658. Min Range: -4.1658
Max Act: 4.0408. Min Act: -0.1700
Data Index: 7803842 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1658. Min Range: -4.1658
Max Act: 3.9782. Min Act: -0.1700
Data Index: 7803850 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1658. Min Range: -4.1658
Max Act: 3.9782. Min Act: -0.1700
Data Index: 7803844 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1658. Min Range: -4.1658
Max Act: 3.9157. Min Act: -0.1700
Data Index: 7803845 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1658. Min Range: -4.1658
Max Act: 3.9157. Min Act: -0.1700
Data Index: 7803847 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1658. Min Range: -4.1658
Max Act: 3.9157. Min Act: -0.1700
Data Index: 7637739 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1658. Min Range: -4.1658
Max Act: 3.8845. Min Act: -0.1700
Data Index: 6473747 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1658. Min Range: -4.1658
Max Act: 3.8845. Min Act: -0.1700
Data Index: 7803848 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1658. Min Range: -4.1658
Max Act: 3.8845. Min Act: -0.1700
Data Index: 6542318 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1658. Min Range: -4.1658
Max Act: 3.8845. Min Act: -0.1700
Data Index: 564714 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1658. Min Range: -4.1658
Max Act: 3.8532. Min Act: -0.1700
Data Index: 2534709 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1658. Min Range: -4.1658
Max Act: 3.8532. Min Act: -0.1700
Data Index: 1482550 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1658. Min Range: -4.1658
Max Act: 3.7594. Min Act: -0.1700
Data Index: 7474021 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1658. Min Range: -4.1658
Max Act: 3.8532. Min Act: -0.1700
Data Index: 7956207 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1658. Min Range: -4.1658
Max Act: 3.8532. Min Act: -0.1700
Data Index: 236895 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19