Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3039 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2739. Min Range: -9.2739
Max Act: 9.2739. Min Act: -0.1700
Data Index: 5723742 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2739. Min Range: -9.2739
Max Act: 9.1489. Min Act: -0.1700
Data Index: 4562140 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2739. Min Range: -9.2739
Max Act: 9.0864. Min Act: -0.1700
Data Index: 473365 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2739. Min Range: -9.2739
Max Act: 9.0239. Min Act: -0.1700
Data Index: 5278295 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2739. Min Range: -9.2739
Max Act: 9.0239. Min Act: -0.1700
Data Index: 2423080 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2739. Min Range: -9.2739
Max Act: 8.9614. Min Act: -0.1700
Data Index: 7931097 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2739. Min Range: -9.2739
Max Act: 8.9614. Min Act: -0.1700
Data Index: 5942911 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2739. Min Range: -9.2739
Max Act: 8.8989. Min Act: -0.1700
Data Index: 3731669 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2739. Min Range: -9.2739
Max Act: 8.8989. Min Act: -0.1700
Data Index: 8478355 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2739. Min Range: -9.2739
Max Act: 8.7739. Min Act: -0.1700
Data Index: 5189269 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2739. Min Range: -9.2739
Max Act: 8.7114. Min Act: -0.1700
Data Index: 1134461 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2739. Min Range: -9.2739
Max Act: 8.7114. Min Act: -0.1700
Data Index: 4121328 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2739. Min Range: -9.2739
Max Act: 8.7114. Min Act: -0.1700
Data Index: 8091345 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2739. Min Range: -9.2739
Max Act: 8.7114. Min Act: -0.1700
Data Index: 3203718 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2739. Min Range: -9.2739
Max Act: 8.6489. Min Act: -0.1700
Data Index: 5465914 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2739. Min Range: -9.2739
Max Act: 8.6489. Min Act: -0.1700
Data Index: 2843632 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2739. Min Range: -9.2739
Max Act: 8.5864. Min Act: -0.1700
Data Index: 7539593 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2739. Min Range: -9.2739
Max Act: 8.5864. Min Act: -0.1700
Data Index: 5042523 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2739. Min Range: -9.2739
Max Act: 8.5239. Min Act: -0.1700
Data Index: 2605562 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2739. Min Range: -9.2739
Max Act: 8.5239. Min Act: -0.1700
Data Index: 911690 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19