Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3546 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0132. Min Range: -9.0132
Max Act: 9.0132. Min Act: -0.1700
Data Index: 3962179 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0132. Min Range: -9.0132
Max Act: 8.8882. Min Act: -0.1700
Data Index: 4060598 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0132. Min Range: -9.0132
Max Act: 8.6382. Min Act: -0.1700
Data Index: 1625311 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0132. Min Range: -9.0132
Max Act: 8.3257. Min Act: -0.1700
Data Index: 2867821 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0132. Min Range: -9.0132
Max Act: 8.3257. Min Act: -0.1700
Data Index: 8330052 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0132. Min Range: -9.0132
Max Act: 8.2007. Min Act: -0.1700
Data Index: 8803974 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0132. Min Range: -9.0132
Max Act: 8.1382. Min Act: -0.1700
Data Index: 580199 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0132. Min Range: -9.0132
Max Act: 8.1070. Min Act: -0.1700
Data Index: 4319670 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0132. Min Range: -9.0132
Max Act: 7.9820. Min Act: -0.1700
Data Index: 8167339 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0132. Min Range: -9.0132
Max Act: 7.9507. Min Act: -0.1700
Data Index: 6662944 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0132. Min Range: -9.0132
Max Act: 7.9507. Min Act: -0.1700
Data Index: 5889701 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0132. Min Range: -9.0132
Max Act: 7.8882. Min Act: -0.1700
Data Index: 2832438 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0132. Min Range: -9.0132
Max Act: 7.8570. Min Act: -0.1700
Data Index: 5486794 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0132. Min Range: -9.0132
Max Act: 7.8882. Min Act: -0.1700
Data Index: 1883692 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0132. Min Range: -9.0132
Max Act: 7.8570. Min Act: -0.1700
Data Index: 4245945 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0132. Min Range: -9.0132
Max Act: 7.8257. Min Act: -0.1700
Data Index: 6138823 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0132. Min Range: -9.0132
Max Act: 7.7945. Min Act: -0.1700
Data Index: 8250592 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0132. Min Range: -9.0132
Max Act: 7.7632. Min Act: -0.1700
Data Index: 4397078 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0132. Min Range: -9.0132
Max Act: 7.7632. Min Act: -0.1700
Data Index: 8098153 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0132. Min Range: -9.0132
Max Act: 7.7320. Min Act: -0.1700
Data Index: 2371909 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19