Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1508 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.7880. Min Act: -0.1700
Data Index: 3423158 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.7880. Min Act: -0.1700
Data Index: 4329177 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.6943. Min Act: -0.1700
Data Index: 6220743 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.6943. Min Act: -0.1700
Data Index: 6437474 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.5693. Min Act: -0.1700
Data Index: 6882967 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.5380. Min Act: -0.1700
Data Index: 553293 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.4755. Min Act: -0.1700
Data Index: 3366529 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.4443. Min Act: -0.1700
Data Index: 4551182 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.4130. Min Act: -0.1700
Data Index: 6367753 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.3818. Min Act: -0.1700
Data Index: 2514670 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.4130. Min Act: -0.1700
Data Index: 6342937 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.3818. Min Act: -0.1700
Data Index: 7788571 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.3818. Min Act: -0.1700
Data Index: 2743721 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.3505. Min Act: -0.1700
Data Index: 5155840 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.3505. Min Act: -0.1700
Data Index: 6042496 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.3505. Min Act: -0.1700
Data Index: 5763922 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.3193. Min Act: -0.1700
Data Index: 7467994 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.3193. Min Act: -0.1700
Data Index: 1595294 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.2880. Min Act: -0.1700
Data Index: 3185797 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7880. Min Range: -5.7880
Max Act: 5.2880. Min Act: -0.1700
Data Index: 1923319 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19