Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.1344. Min Range: -9.1344
Max Act: 9.1344. Min Act: -0.1700
Data Index: 4568422 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1344. Min Range: -9.1344
Max Act: 9.0719. Min Act: -0.1700
Data Index: 2247618 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1344. Min Range: -9.1344
Max Act: 9.0094. Min Act: -0.1700
Data Index: 1626771 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1344. Min Range: -9.1344
Max Act: 8.8844. Min Act: -0.1700
Data Index: 1792367 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1344. Min Range: -9.1344
Max Act: 8.7594. Min Act: -0.1700
Data Index: 5505850 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1344. Min Range: -9.1344
Max Act: 8.6969. Min Act: -0.1700
Data Index: 5598024 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1344. Min Range: -9.1344
Max Act: 8.6969. Min Act: -0.1700
Data Index: 7808162 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1344. Min Range: -9.1344
Max Act: 8.6344. Min Act: -0.1700
Data Index: 6942683 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1344. Min Range: -9.1344
Max Act: 8.5719. Min Act: -0.1700
Data Index: 1332664 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1344. Min Range: -9.1344
Max Act: 8.5719. Min Act: -0.1700
Data Index: 1635711 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1344. Min Range: -9.1344
Max Act: 8.5719. Min Act: -0.1700
Data Index: 2643487 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1344. Min Range: -9.1344
Max Act: 8.4469. Min Act: -0.1700
Data Index: 6070331 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1344. Min Range: -9.1344
Max Act: 8.5094. Min Act: -0.1700
Data Index: 297072 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1344. Min Range: -9.1344
Max Act: 8.5094. Min Act: -0.1700
Data Index: 4454102 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1344. Min Range: -9.1344
Max Act: 8.3844. Min Act: -0.1700
Data Index: 259700 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1344. Min Range: -9.1344
Max Act: 8.3219. Min Act: -0.1700
Data Index: 3963245 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1344. Min Range: -9.1344
Max Act: 8.3844. Min Act: -0.1700
Data Index: 8327544 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1344. Min Range: -9.1344
Max Act: 8.3219. Min Act: -0.1700
Data Index: 5333523 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1344. Min Range: -9.1344
Max Act: 8.3219. Min Act: -0.1700
Data Index: 5711702 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1344. Min Range: -9.1344
Max Act: 8.2594. Min Act: -0.1700
Data Index: 6158524 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19