Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 891 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0290. Min Range: -5.0290
Max Act: 5.0290. Min Act: -0.1700
Data Index: 2770618 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0290. Min Range: -5.0290
Max Act: 5.0290. Min Act: -0.1700
Data Index: 3318059 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.9665. Min Act: -0.1700
Data Index: 1143498 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.8727. Min Act: -0.1700
Data Index: 2860222 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.9040. Min Act: -0.1700
Data Index: 5113109 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.8415. Min Act: -0.1700
Data Index: 2177436 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.8102. Min Act: -0.1700
Data Index: 8137645 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.8102. Min Act: -0.1700
Data Index: 2493824 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.8102. Min Act: -0.1700
Data Index: 160891 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.7477. Min Act: -0.1700
Data Index: 2770617 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.7790. Min Act: -0.1700
Data Index: 3517388 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.7790. Min Act: -0.1700
Data Index: 7480731 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.7165. Min Act: -0.1700
Data Index: 1549838 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.6852. Min Act: -0.1700
Data Index: 4449385 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.7477. Min Act: -0.1700
Data Index: 3522161 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.6852. Min Act: -0.1700
Data Index: 101400 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.6852. Min Act: -0.1700
Data Index: 7908297 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.7165. Min Act: -0.1700
Data Index: 7834296 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.6852. Min Act: -0.1700
Data Index: 2770610 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0290. Min Range: -5.0290
Max Act: 4.6540. Min Act: -0.1700
Data Index: 7730467 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19