Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3617 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0396. Min Range: -4.0396
Max Act: 4.0396. Min Act: -0.1700
Data Index: 2884335 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.9771. Min Act: -0.1700
Data Index: 4630361 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.9458. Min Act: -0.1700
Data Index: 1456084 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.8833. Min Act: -0.1700
Data Index: 8608360 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.8208. Min Act: -0.1700
Data Index: 2771405 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.7582. Min Act: -0.1700
Data Index: 3064516 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.7582. Min Act: -0.1700
Data Index: 4469891 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.6800. Min Act: -0.1700
Data Index: 5409866 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.6331. Min Act: -0.1700
Data Index: 3313252 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.6174. Min Act: -0.1700
Data Index: 5833029 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.6018. Min Act: -0.1700
Data Index: 5922675 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.6018. Min Act: -0.1700
Data Index: 490430 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.5861. Min Act: -0.1700
Data Index: 5114921 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.6018. Min Act: -0.1700
Data Index: 4469901 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.6018. Min Act: -0.1700
Data Index: 103195 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.5861. Min Act: -0.1700
Data Index: 6533967 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.5705. Min Act: -0.1700
Data Index: 4425866 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.5548. Min Act: -0.1700
Data Index: 7113257 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.5548. Min Act: -0.1700
Data Index: 4469899 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0396. Min Range: -4.0396
Max Act: 3.5392. Min Act: -0.1700
Data Index: 4055894 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19