Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1281 in Layer 0
Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')
Click the toggle to see the full text!
Text #0
Max Range: 4.3557. Min Range: -4.3557
Max Act: 4.3557. Min Act: -0.1700
Data Index: 6357282 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 4.3557. Min Range: -4.3557
Max Act: 4.3207. Min Act: -0.1700
Data Index: 6357302 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 4.3557. Min Range: -4.3557
Max Act: 4.0721. Min Act: -0.1700
Data Index: 6357283 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 4.3557. Min Range: -4.3557
Max Act: 3.9535. Min Act: -0.1700
Data Index: 7984066 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 4.3557. Min Range: -4.3557
Max Act: 3.9433. Min Act: -0.1700
Data Index: 5013156 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 4.3557. Min Range: -4.3557
Max Act: 3.9033. Min Act: -0.1700
Data Index: 700197 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 4.3557. Min Range: -4.3557
Max Act: 3.9037. Min Act: -0.1700
Data Index: 7529218 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 4.3557. Min Range: -4.3557
Max Act: 3.8556. Min Act: -0.1700
Data Index: 718408 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 4.3557. Min Range: -4.3557
Max Act: 3.8864. Min Act: -0.1700
Data Index: 6357299 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 4.3557. Min Range: -4.3557
Max Act: 3.8662. Min Act: -0.1700
Data Index: 8305868 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 4.3557. Min Range: -4.3557
Max Act: 3.8592. Min Act: -0.1700
Data Index: 6357279 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 4.3557. Min Range: -4.3557
Max Act: 3.8424. Min Act: -0.1700
Data Index: 3490678 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 4.3557. Min Range: -4.3557
Max Act: 3.8550. Min Act: -0.1700
Data Index: 2968157 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 4.3557. Min Range: -4.3557
Max Act: 3.8421. Min Act: -0.1700
Data Index: 5313552 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 4.3557. Min Range: -4.3557
Max Act: 3.8482. Min Act: -0.1700
Data Index: 8732644 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 4.3557. Min Range: -4.3557
Max Act: 3.8359. Min Act: -0.1700
Data Index: 6357296 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 4.3557. Min Range: -4.3557
Max Act: 3.8331. Min Act: -0.1699
Data Index: 7091874 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 4.3557. Min Range: -4.3557
Max Act: 3.8113. Min Act: -0.1700
Data Index: 7035063 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 4.3557. Min Range: -4.3557
Max Act: 3.8206. Min Act: -0.1700
Data Index: 8328113 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 4.3557. Min Range: -4.3557
Max Act: 3.8155. Min Act: -0.1700
Data Index: 8370048 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full textTruncated
Full Text #19