Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3561 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.6510. Min Act: -0.1700
Data Index: 1908376 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.5572. Min Act: -0.1700
Data Index: 3103064 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.4635. Min Act: -0.1700
Data Index: 1982160 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.4322. Min Act: -0.1700
Data Index: 803554 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.4010. Min Act: -0.1700
Data Index: 5364111 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.4010. Min Act: -0.1700
Data Index: 8766548 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.3697. Min Act: -0.1700
Data Index: 7628195 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.3385. Min Act: -0.1700
Data Index: 5234950 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.2447. Min Act: -0.1700
Data Index: 2312806 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.2760. Min Act: -0.1700
Data Index: 4449789 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.2760. Min Act: -0.1700
Data Index: 3412973 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.2760. Min Act: -0.1700
Data Index: 5263156 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.2447. Min Act: -0.1700
Data Index: 6554923 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.1822. Min Act: -0.1700
Data Index: 7845639 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.2135. Min Act: -0.1700
Data Index: 5214822 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.1822. Min Act: -0.1700
Data Index: 6245613 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.1822. Min Act: -0.1700
Data Index: 8082181 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.1822. Min Act: -0.1700
Data Index: 2467521 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.1822. Min Act: -0.1700
Data Index: 7384830 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6510. Min Range: -5.6510
Max Act: 5.1510. Min Act: -0.1700
Data Index: 6936102 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19