Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1724 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.1893. Min Act: -0.1700
Data Index: 4618917 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.1727. Min Act: -0.1700
Data Index: 6000313 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.1394. Min Act: -0.1700
Data Index: 4122949 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.1561. Min Act: -0.1700
Data Index: 3169708 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.1561. Min Act: -0.1700
Data Index: 4714165 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.1394. Min Act: -0.1700
Data Index: 2483788 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.1561. Min Act: -0.1700
Data Index: 645826 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.1394. Min Act: -0.1700
Data Index: 4140589 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.1394. Min Act: -0.1700
Data Index: 4219159 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.1227. Min Act: -0.1700
Data Index: 6951509 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.1060. Min Act: -0.1700
Data Index: 2216690 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.1060. Min Act: -0.1699
Data Index: 5364646 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.0892. Min Act: -0.1700
Data Index: 7742695 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.0724. Min Act: -0.1700
Data Index: 5396215 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.0724. Min Act: -0.1699
Data Index: 493221 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.0388. Min Act: -0.1700
Data Index: 7918358 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.0724. Min Act: -0.1700
Data Index: 5995538 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.0556. Min Act: -0.1700
Data Index: 2133681 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.0724. Min Act: -0.1700
Data Index: 6061846 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1893. Min Range: -2.1893
Max Act: 2.0892. Min Act: -0.1700
Data Index: 1212588 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19