Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4503 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0709. Min Range: -7.0709
Max Act: 7.0709. Min Act: -0.1700
Data Index: 7295396 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0709. Min Range: -7.0709
Max Act: 7.0084. Min Act: -0.1700
Data Index: 3646843 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.8522. Min Act: -0.1700
Data Index: 3159324 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.8209. Min Act: -0.1700
Data Index: 306699 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.7897. Min Act: -0.1700
Data Index: 5266662 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.7584. Min Act: -0.1700
Data Index: 6643899 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.7584. Min Act: -0.1700
Data Index: 1910401 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.6959. Min Act: -0.1700
Data Index: 7453668 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.7272. Min Act: -0.1700
Data Index: 3921172 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.6334. Min Act: -0.1700
Data Index: 5718270 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.6334. Min Act: -0.1700
Data Index: 5210261 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.6334. Min Act: -0.1700
Data Index: 280911 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.6022. Min Act: -0.1700
Data Index: 7392553 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.6022. Min Act: -0.1700
Data Index: 3159320 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.5709. Min Act: -0.1700
Data Index: 4542619 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.5397. Min Act: -0.1700
Data Index: 2626771 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.5709. Min Act: -0.1700
Data Index: 1476716 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.5709. Min Act: -0.1700
Data Index: 7325286 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.5397. Min Act: -0.1700
Data Index: 280910 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0709. Min Range: -7.0709
Max Act: 6.5397. Min Act: -0.1700
Data Index: 5609292 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19