Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1373 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2038. Min Range: -7.2038
Max Act: 7.2038. Min Act: -0.1700
Data Index: 8573561 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2038. Min Range: -7.2038
Max Act: 7.1725. Min Act: -0.1700
Data Index: 2396986 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2038. Min Range: -7.2038
Max Act: 7.1413. Min Act: -0.1700
Data Index: 185404 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2038. Min Range: -7.2038
Max Act: 7.0163. Min Act: -0.1700
Data Index: 6790789 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2038. Min Range: -7.2038
Max Act: 6.9850. Min Act: -0.1700
Data Index: 6852920 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2038. Min Range: -7.2038
Max Act: 6.9225. Min Act: -0.1700
Data Index: 1550112 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2038. Min Range: -7.2038
Max Act: 6.8913. Min Act: -0.1700
Data Index: 6918486 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2038. Min Range: -7.2038
Max Act: 6.8288. Min Act: -0.1700
Data Index: 5034529 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2038. Min Range: -7.2038
Max Act: 6.8600. Min Act: -0.1700
Data Index: 3864790 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2038. Min Range: -7.2038
Max Act: 6.8288. Min Act: -0.1700
Data Index: 2231619 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2038. Min Range: -7.2038
Max Act: 6.8288. Min Act: -0.1700
Data Index: 3932765 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2038. Min Range: -7.2038
Max Act: 6.7975. Min Act: -0.1700
Data Index: 93357 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2038. Min Range: -7.2038
Max Act: 6.7038. Min Act: -0.1700
Data Index: 1265641 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2038. Min Range: -7.2038
Max Act: 6.7038. Min Act: -0.1700
Data Index: 6919576 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2038. Min Range: -7.2038
Max Act: 6.6413. Min Act: -0.1700
Data Index: 4365376 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2038. Min Range: -7.2038
Max Act: 6.6100. Min Act: -0.1700
Data Index: 7259156 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2038. Min Range: -7.2038
Max Act: 6.6100. Min Act: -0.1700
Data Index: 7045106 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2038. Min Range: -7.2038
Max Act: 6.5788. Min Act: -0.1700
Data Index: 6916226 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2038. Min Range: -7.2038
Max Act: 6.5788. Min Act: -0.1700
Data Index: 2346731 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2038. Min Range: -7.2038
Max Act: 6.5475. Min Act: -0.1700
Data Index: 8324798 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19