Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4520 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.8687. Min Act: -0.1700
Data Index: 5822022 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.8051. Min Act: -0.1700
Data Index: 7745326 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.8051. Min Act: -0.1700
Data Index: 8519239 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.7732. Min Act: -0.1700
Data Index: 221769 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.7573. Min Act: -0.1700
Data Index: 263692 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.7413. Min Act: -0.1700
Data Index: 7732260 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.7253. Min Act: -0.1700
Data Index: 3393648 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.7253. Min Act: -0.1700
Data Index: 771522 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.7093. Min Act: -0.1700
Data Index: 6326894 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.7093. Min Act: -0.1700
Data Index: 8569066 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.6933. Min Act: -0.1700
Data Index: 4017317 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.6933. Min Act: -0.1700
Data Index: 3998107 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.6933. Min Act: -0.1700
Data Index: 3228738 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.6773. Min Act: -0.1700
Data Index: 263690 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.6773. Min Act: -0.1700
Data Index: 7745324 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.6773. Min Act: -0.1700
Data Index: 290875 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.6773. Min Act: -0.1700
Data Index: 8638398 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.6613. Min Act: -0.1700
Data Index: 750836 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.6613. Min Act: -0.1700
Data Index: 4487239 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8687. Min Range: -2.8687
Max Act: 2.6292. Min Act: -0.1700
Data Index: 1960953 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19