Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3805 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4070. Min Range: -6.4070
Max Act: 6.4070. Min Act: -0.1700
Data Index: 4834716 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4070. Min Range: -6.4070
Max Act: 6.2195. Min Act: -0.1700
Data Index: 5281969 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4070. Min Range: -6.4070
Max Act: 6.2195. Min Act: -0.1700
Data Index: 5750692 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4070. Min Range: -6.4070
Max Act: 6.1883. Min Act: -0.1700
Data Index: 8801284 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4070. Min Range: -6.4070
Max Act: 6.1258. Min Act: -0.1700
Data Index: 7433438 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4070. Min Range: -6.4070
Max Act: 6.1258. Min Act: -0.1700
Data Index: 5281963 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4070. Min Range: -6.4070
Max Act: 6.0320. Min Act: -0.1583
Data Index: 8801283 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4070. Min Range: -6.4070
Max Act: 6.0008. Min Act: -0.1700
Data Index: 5750691 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4070. Min Range: -6.4070
Max Act: 6.0008. Min Act: -0.1698
Data Index: 4834717 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4070. Min Range: -6.4070
Max Act: 6.0008. Min Act: -0.1700
Data Index: 6907754 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4070. Min Range: -6.4070
Max Act: 5.9695. Min Act: -0.1700
Data Index: 7866372 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4070. Min Range: -6.4070
Max Act: 5.9070. Min Act: -0.1661
Data Index: 7506304 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4070. Min Range: -6.4070
Max Act: 5.9070. Min Act: -0.1681
Data Index: 2871445 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4070. Min Range: -6.4070
Max Act: 5.8758. Min Act: -0.1700
Data Index: 5281965 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4070. Min Range: -6.4070
Max Act: 5.8758. Min Act: -0.1700
Data Index: 5983398 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4070. Min Range: -6.4070
Max Act: 5.8758. Min Act: -0.1700
Data Index: 6907753 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4070. Min Range: -6.4070
Max Act: 5.8445. Min Act: -0.1700
Data Index: 6887939 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4070. Min Range: -6.4070
Max Act: 5.8445. Min Act: -0.1700
Data Index: 5706189 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4070. Min Range: -6.4070
Max Act: 5.8445. Min Act: -0.1700
Data Index: 810056 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4070. Min Range: -6.4070
Max Act: 5.8758. Min Act: -0.1700
Data Index: 5746951 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19