Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5112 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0552. Min Range: -7.0552
Max Act: 7.0552. Min Act: -0.1700
Data Index: 1739946 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.7114. Min Act: -0.1700
Data Index: 8093866 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.6802. Min Act: -0.1700
Data Index: 7951621 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.6489. Min Act: -0.1700
Data Index: 7903823 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.6177. Min Act: -0.1700
Data Index: 614263 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.4927. Min Act: -0.1700
Data Index: 6788609 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.4927. Min Act: -0.1700
Data Index: 615884 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.4614. Min Act: -0.1700
Data Index: 3318949 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.4614. Min Act: -0.1700
Data Index: 7567501 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.4302. Min Act: -0.1700
Data Index: 7508976 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.3989. Min Act: -0.1700
Data Index: 5340347 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.3989. Min Act: -0.1700
Data Index: 22790 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.3989. Min Act: -0.1700
Data Index: 5329009 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.4302. Min Act: -0.1700
Data Index: 3112903 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.3677. Min Act: -0.1700
Data Index: 2153784 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.3677. Min Act: -0.1700
Data Index: 6064380 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.3677. Min Act: -0.1700
Data Index: 7108923 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.3677. Min Act: -0.1700
Data Index: 1985987 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.3677. Min Act: -0.1700
Data Index: 2780022 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0552. Min Range: -7.0552
Max Act: 6.3364. Min Act: -0.1700
Data Index: 7199244 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19