Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3600 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6967. Min Range: -7.6967
Max Act: 7.6967. Min Act: -0.1700
Data Index: 7466328 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6967. Min Range: -7.6967
Max Act: 7.6967. Min Act: -0.1700
Data Index: 5102819 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6967. Min Range: -7.6967
Max Act: 7.6342. Min Act: -0.1700
Data Index: 4400037 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6967. Min Range: -7.6967
Max Act: 7.2592. Min Act: -0.1700
Data Index: 3843459 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6967. Min Range: -7.6967
Max Act: 7.1967. Min Act: -0.1700
Data Index: 6323685 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6967. Min Range: -7.6967
Max Act: 7.1654. Min Act: -0.1700
Data Index: 6141894 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6967. Min Range: -7.6967
Max Act: 7.0404. Min Act: -0.1700
Data Index: 4005035 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6967. Min Range: -7.6967
Max Act: 7.0092. Min Act: -0.1700
Data Index: 3911789 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6967. Min Range: -7.6967
Max Act: 7.0092. Min Act: -0.1700
Data Index: 540243 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6967. Min Range: -7.6967
Max Act: 7.0092. Min Act: -0.1700
Data Index: 568579 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6967. Min Range: -7.6967
Max Act: 7.0092. Min Act: -0.1700
Data Index: 7603203 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6967. Min Range: -7.6967
Max Act: 6.9779. Min Act: -0.1700
Data Index: 1179284 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6967. Min Range: -7.6967
Max Act: 6.9779. Min Act: -0.1700
Data Index: 8695744 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6967. Min Range: -7.6967
Max Act: 6.9467. Min Act: -0.1700
Data Index: 5309014 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6967. Min Range: -7.6967
Max Act: 6.9779. Min Act: -0.1700
Data Index: 303928 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6967. Min Range: -7.6967
Max Act: 6.9779. Min Act: -0.1700
Data Index: 8316790 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6967. Min Range: -7.6967
Max Act: 6.9467. Min Act: -0.1700
Data Index: 8203199 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6967. Min Range: -7.6967
Max Act: 6.9154. Min Act: -0.1700
Data Index: 6169119 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6967. Min Range: -7.6967
Max Act: 6.8842. Min Act: -0.1700
Data Index: 5347840 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6967. Min Range: -7.6967
Max Act: 6.9154. Min Act: -0.1700
Data Index: 4470186 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19