Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2824 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.7827. Min Act: -0.1700
Data Index: 2952555 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.7202. Min Act: -0.1700
Data Index: 5704873 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.6264. Min Act: -0.1700
Data Index: 941382 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.5952. Min Act: -0.1700
Data Index: 5164264 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.5952. Min Act: -0.1700
Data Index: 5867901 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.5952. Min Act: -0.1700
Data Index: 3249639 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.5952. Min Act: -0.1700
Data Index: 8826343 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.5952. Min Act: -0.1700
Data Index: 310651 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.5639. Min Act: -0.1700
Data Index: 2790593 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.5014. Min Act: -0.1700
Data Index: 2909324 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.5014. Min Act: -0.1700
Data Index: 7370570 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.4702. Min Act: -0.1700
Data Index: 1271358 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.5327. Min Act: -0.1700
Data Index: 5701533 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.5327. Min Act: -0.1700
Data Index: 1295789 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.5014. Min Act: -0.1700
Data Index: 4146188 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.5014. Min Act: -0.1700
Data Index: 5630184 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.4702. Min Act: -0.1700
Data Index: 6586475 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.4702. Min Act: -0.1700
Data Index: 3273231 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.4702. Min Act: -0.1700
Data Index: 3574848 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7827. Min Range: -5.7827
Max Act: 5.4389. Min Act: -0.1700
Data Index: 6200449 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19