Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2680 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.9514. Min Act: -0.1700
Data Index: 2621199 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.7326. Min Act: -0.1700
Data Index: 2621198 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.7014. Min Act: -0.1700
Data Index: 128924 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.7014. Min Act: -0.1700
Data Index: 2654010 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.6389. Min Act: -0.1700
Data Index: 5875377 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.6389. Min Act: -0.1700
Data Index: 8539963 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.6076. Min Act: -0.1700
Data Index: 8659649 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.5764. Min Act: -0.1700
Data Index: 7196282 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.6076. Min Act: -0.1700
Data Index: 7347027 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.5764. Min Act: -0.1700
Data Index: 493704 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.4826. Min Act: -0.1700
Data Index: 3105531 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.4514. Min Act: -0.1700
Data Index: 8356322 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.3576. Min Act: -0.1700
Data Index: 6564245 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.3576. Min Act: -0.1700
Data Index: 8145852 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.4201. Min Act: -0.1700
Data Index: 1894132 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.3576. Min Act: -0.1700
Data Index: 4748189 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.3889. Min Act: -0.1700
Data Index: 1870292 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.4201. Min Act: -0.1700
Data Index: 5875376 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.3889. Min Act: -0.1700
Data Index: 8256397 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9514. Min Range: -5.9514
Max Act: 5.3576. Min Act: -0.1700
Data Index: 3193747 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19