Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3960 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.9785. Min Act: -0.1700
Data Index: 3487676 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.5718. Min Act: -0.1700
Data Index: 3487681 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.5248. Min Act: -0.1700
Data Index: 4566901 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.5405. Min Act: -0.1700
Data Index: 8131029 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.5248. Min Act: -0.1700
Data Index: 1941214 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.4935. Min Act: -0.1700
Data Index: 7719977 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.4935. Min Act: -0.1700
Data Index: 1714757 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.4935. Min Act: -0.1700
Data Index: 6476255 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.4779. Min Act: -0.1700
Data Index: 8131027 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.4779. Min Act: -0.1700
Data Index: 6177972 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.4779. Min Act: -0.1700
Data Index: 8131020 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.4779. Min Act: -0.1700
Data Index: 6887383 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.4465. Min Act: -0.1700
Data Index: 8131022 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.4465. Min Act: -0.1700
Data Index: 1706663 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.4465. Min Act: -0.1700
Data Index: 3784261 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.4309. Min Act: -0.1700
Data Index: 125971 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.4309. Min Act: -0.1700
Data Index: 8702508 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.4465. Min Act: -0.1700
Data Index: 5671317 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.4309. Min Act: -0.1700
Data Index: 609040 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9785. Min Range: -3.9785
Max Act: 3.4309. Min Act: -0.1700
Data Index: 4952923 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19