Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3167 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0883. Min Range: -8.0883
Max Act: 8.0883. Min Act: -0.1700
Data Index: 8689993 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.9008. Min Act: -0.1700
Data Index: 5979570 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.9008. Min Act: -0.1700
Data Index: 4320114 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.9008. Min Act: -0.1700
Data Index: 5255928 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.8383. Min Act: -0.1700
Data Index: 5415749 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.9008. Min Act: -0.1700
Data Index: 4675329 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.7758. Min Act: -0.1700
Data Index: 1939481 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.7758. Min Act: -0.1700
Data Index: 7081752 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.7758. Min Act: -0.1700
Data Index: 721980 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.7758. Min Act: -0.1700
Data Index: 6587758 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.7133. Min Act: -0.1700
Data Index: 2728661 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.7133. Min Act: -0.1700
Data Index: 2936203 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.7133. Min Act: -0.1700
Data Index: 6554331 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.5883. Min Act: -0.1700
Data Index: 2508969 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.5883. Min Act: -0.1700
Data Index: 7691520 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.5883. Min Act: -0.1700
Data Index: 4697081 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.5883. Min Act: -0.1700
Data Index: 7769875 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.5571. Min Act: -0.1700
Data Index: 742591 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.5258. Min Act: -0.1700
Data Index: 3684870 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0883. Min Range: -8.0883
Max Act: 7.5571. Min Act: -0.1700
Data Index: 7389644 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19