Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1988 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.8149. Min Act: -0.1700
Data Index: 8751831 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.7524. Min Act: -0.1700
Data Index: 7234828 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.7211. Min Act: -0.1700
Data Index: 6270086 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.6586. Min Act: -0.1700
Data Index: 1411710 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.5961. Min Act: -0.1700
Data Index: 7067618 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.5961. Min Act: -0.1700
Data Index: 2155401 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.5649. Min Act: -0.1700
Data Index: 8751830 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.5336. Min Act: -0.1700
Data Index: 819768 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.5336. Min Act: -0.1700
Data Index: 6270087 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.5336. Min Act: -0.1700
Data Index: 230163 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.5024. Min Act: -0.1700
Data Index: 5209377 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.4711. Min Act: -0.1700
Data Index: 929739 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.4399. Min Act: -0.1700
Data Index: 4810133 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.4711. Min Act: -0.1700
Data Index: 6455649 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.4711. Min Act: -0.1700
Data Index: 3820332 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.4711. Min Act: -0.1700
Data Index: 3651735 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.4086. Min Act: -0.1700
Data Index: 4810131 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.4399. Min Act: -0.1700
Data Index: 7067623 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.4399. Min Act: -0.1700
Data Index: 819769 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8149. Min Range: -5.8149
Max Act: 5.4399. Min Act: -0.1700
Data Index: 1007297 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19