Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1932 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.3480. Min Act: -0.1700
Data Index: 2084188 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.2855. Min Act: -0.1700
Data Index: 4651493 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.2230. Min Act: -0.1699
Data Index: 4041331 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.2230. Min Act: -0.1700
Data Index: 4059688 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.2230. Min Act: -0.1700
Data Index: 4300149 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.1605. Min Act: -0.1700
Data Index: 2806488 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.2230. Min Act: -0.1700
Data Index: 7148233 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.1605. Min Act: -0.1700
Data Index: 1858304 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.1605. Min Act: -0.1700
Data Index: 3549557 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.1605. Min Act: -0.1700
Data Index: 7276418 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.1605. Min Act: -0.1700
Data Index: 1086884 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.1605. Min Act: -0.1700
Data Index: 5882921 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.1605. Min Act: -0.1700
Data Index: 5792725 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.0980. Min Act: -0.1700
Data Index: 4330655 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.1605. Min Act: -0.1700
Data Index: 2638210 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.1605. Min Act: -0.1700
Data Index: 4089332 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.1605. Min Act: -0.1700
Data Index: 1753831 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.0980. Min Act: -0.1700
Data Index: 45420 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.0980. Min Act: -0.1700
Data Index: 3570653 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3480. Min Range: -7.3480
Max Act: 7.0980. Min Act: -0.1700
Data Index: 2243988 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19