Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 976 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.8388. Min Act: -0.1700
Data Index: 8477259 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.7763. Min Act: -0.1700
Data Index: 7833763 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.6513. Min Act: -0.1700
Data Index: 4306722 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.5263. Min Act: -0.1700
Data Index: 6563413 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.5888. Min Act: -0.1700
Data Index: 4184641 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.6513. Min Act: -0.1700
Data Index: 4243753 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.5888. Min Act: -0.1700
Data Index: 5083419 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.5263. Min Act: -0.1700
Data Index: 2063948 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.4638. Min Act: -0.1700
Data Index: 185049 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.4013. Min Act: -0.1700
Data Index: 3976661 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.3388. Min Act: -0.1700
Data Index: 8211512 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.4013. Min Act: -0.1700
Data Index: 6376728 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.2763. Min Act: -0.1700
Data Index: 6591725 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.2450. Min Act: -0.1700
Data Index: 2811727 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.2763. Min Act: -0.1700
Data Index: 4263565 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.2763. Min Act: -0.1700
Data Index: 1259499 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.2450. Min Act: -0.1700
Data Index: 2892006 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.2450. Min Act: -0.1700
Data Index: 8226766 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.2450. Min Act: -0.1700
Data Index: 2280223 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8388. Min Range: -7.8388
Max Act: 7.2138. Min Act: -0.1700
Data Index: 8316069 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19