Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 650 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2739. Min Range: -7.2739
Max Act: 7.2739. Min Act: -0.1700
Data Index: 1213231 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2739. Min Range: -7.2739
Max Act: 7.0864. Min Act: -0.1700
Data Index: 1169001 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.8364. Min Act: -0.1700
Data Index: 883159 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.8364. Min Act: -0.1700
Data Index: 6619875 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.7739. Min Act: -0.1700
Data Index: 2109080 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.7427. Min Act: -0.1700
Data Index: 1938903 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.7427. Min Act: -0.1700
Data Index: 4160271 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.7114. Min Act: -0.1700
Data Index: 5126699 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.7114. Min Act: -0.1700
Data Index: 5126693 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.7427. Min Act: -0.1700
Data Index: 7254787 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.7114. Min Act: -0.1700
Data Index: 6705771 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.7114. Min Act: -0.1700
Data Index: 6171235 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.6802. Min Act: -0.1700
Data Index: 5126696 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.6802. Min Act: -0.1700
Data Index: 4079439 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.6489. Min Act: -0.1700
Data Index: 5584362 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.6177. Min Act: -0.1700
Data Index: 7938953 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.6489. Min Act: -0.1700
Data Index: 7791132 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.6177. Min Act: -0.1700
Data Index: 3431630 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.5864. Min Act: -0.1700
Data Index: 1581179 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2739. Min Range: -7.2739
Max Act: 6.5864. Min Act: -0.1700
Data Index: 1468294 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19