Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 43 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.4693. Min Act: -0.1700
Data Index: 3563779 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.3131. Min Act: -0.1700
Data Index: 6441477 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.3131. Min Act: -0.1700
Data Index: 5818152 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.2818. Min Act: -0.1698
Data Index: 3193606 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.2506. Min Act: -0.1700
Data Index: 4241939 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.2506. Min Act: -0.1700
Data Index: 5255668 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.2506. Min Act: -0.1699
Data Index: 5793199 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.2193. Min Act: -0.1700
Data Index: 6055822 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.1881. Min Act: -0.1700
Data Index: 1628149 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.1881. Min Act: -0.1700
Data Index: 5347640 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.1256. Min Act: -0.1700
Data Index: 5878076 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.1256. Min Act: -0.1700
Data Index: 1655896 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.1256. Min Act: -0.1700
Data Index: 7701080 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.0943. Min Act: -0.1700
Data Index: 687684 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.1256. Min Act: -0.1700
Data Index: 114773 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.0631. Min Act: -0.1700
Data Index: 6950086 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.0943. Min Act: -0.1699
Data Index: 7446699 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.0943. Min Act: -0.1700
Data Index: 2621019 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.0943. Min Act: -0.1700
Data Index: 932777 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4693. Min Range: -6.4693
Max Act: 6.0943. Min Act: -0.1700
Data Index: 7878917 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19