Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1722 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6537. Min Range: -7.6537
Max Act: 7.6537. Min Act: -0.1700
Data Index: 6780977 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6537. Min Range: -7.6537
Max Act: 7.6537. Min Act: -0.1700
Data Index: 2035010 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6537. Min Range: -7.6537
Max Act: 7.5287. Min Act: -0.1700
Data Index: 1297028 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6537. Min Range: -7.6537
Max Act: 7.4662. Min Act: -0.1700
Data Index: 8674058 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6537. Min Range: -7.6537
Max Act: 7.3725. Min Act: -0.1700
Data Index: 3843626 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6537. Min Range: -7.6537
Max Act: 7.1537. Min Act: -0.1700
Data Index: 172281 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6537. Min Range: -7.6537
Max Act: 7.0912. Min Act: -0.1700
Data Index: 5714237 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6537. Min Range: -7.6537
Max Act: 7.1225. Min Act: -0.1700
Data Index: 1161229 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6537. Min Range: -7.6537
Max Act: 7.0912. Min Act: -0.1700
Data Index: 2690399 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6537. Min Range: -7.6537
Max Act: 7.0600. Min Act: -0.1700
Data Index: 8356598 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6537. Min Range: -7.6537
Max Act: 7.0912. Min Act: -0.1700
Data Index: 6754852 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6537. Min Range: -7.6537
Max Act: 7.0287. Min Act: -0.1700
Data Index: 2080050 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6537. Min Range: -7.6537
Max Act: 7.0600. Min Act: -0.1700
Data Index: 2184992 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6537. Min Range: -7.6537
Max Act: 7.0287. Min Act: -0.1700
Data Index: 1559176 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6537. Min Range: -7.6537
Max Act: 6.9975. Min Act: -0.1700
Data Index: 3564638 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6537. Min Range: -7.6537
Max Act: 6.9975. Min Act: -0.1700
Data Index: 319566 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6537. Min Range: -7.6537
Max Act: 6.9662. Min Act: -0.1700
Data Index: 6262960 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6537. Min Range: -7.6537
Max Act: 6.9662. Min Act: -0.1700
Data Index: 4514581 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6537. Min Range: -7.6537
Max Act: 6.9662. Min Act: -0.1700
Data Index: 5621329 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6537. Min Range: -7.6537
Max Act: 6.9037. Min Act: -0.1700
Data Index: 7045030 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19