Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5450 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7836. Min Range: -6.7836
Max Act: 6.7836. Min Act: -0.1700
Data Index: 6766895 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7836. Min Range: -6.7836
Max Act: 6.7211. Min Act: -0.1700
Data Index: 884037 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7836. Min Range: -6.7836
Max Act: 6.3774. Min Act: -0.1700
Data Index: 2017304 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7836. Min Range: -6.7836
Max Act: 6.4086. Min Act: -0.1700
Data Index: 6190555 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7836. Min Range: -6.7836
Max Act: 6.2836. Min Act: -0.1700
Data Index: 897278 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7836. Min Range: -6.7836
Max Act: 6.2524. Min Act: -0.1700
Data Index: 7967889 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7836. Min Range: -6.7836
Max Act: 6.2211. Min Act: -0.1700
Data Index: 8531311 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7836. Min Range: -6.7836
Max Act: 6.1274. Min Act: -0.1700
Data Index: 2843274 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7836. Min Range: -6.7836
Max Act: 6.1274. Min Act: -0.1700
Data Index: 5917367 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7836. Min Range: -6.7836
Max Act: 6.0961. Min Act: -0.1700
Data Index: 2451854 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7836. Min Range: -6.7836
Max Act: 6.0961. Min Act: -0.1700
Data Index: 389189 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7836. Min Range: -6.7836
Max Act: 6.0649. Min Act: -0.1700
Data Index: 2412503 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7836. Min Range: -6.7836
Max Act: 6.0024. Min Act: -0.1700
Data Index: 1032993 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7836. Min Range: -6.7836
Max Act: 6.0024. Min Act: -0.1700
Data Index: 4239201 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7836. Min Range: -6.7836
Max Act: 5.9711. Min Act: -0.1700
Data Index: 1012673 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7836. Min Range: -6.7836
Max Act: 6.0024. Min Act: -0.1700
Data Index: 3623063 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7836. Min Range: -6.7836
Max Act: 6.0024. Min Act: -0.1700
Data Index: 7323734 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7836. Min Range: -6.7836
Max Act: 5.9711. Min Act: -0.1700
Data Index: 7489950 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7836. Min Range: -6.7836
Max Act: 5.9399. Min Act: -0.1700
Data Index: 4766442 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7836. Min Range: -6.7836
Max Act: 5.9711. Min Act: -0.1700
Data Index: 2170141 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19