Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4186 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.7020. Min Act: -0.1700
Data Index: 2265089 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.6395. Min Act: -0.1700
Data Index: 7639764 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.6395. Min Act: -0.1700
Data Index: 2555967 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.5770. Min Act: -0.1700
Data Index: 4353261 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.5145. Min Act: -0.1700
Data Index: 7260584 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.5145. Min Act: -0.1700
Data Index: 1994656 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.5145. Min Act: -0.1700
Data Index: 1541983 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.4833. Min Act: -0.1700
Data Index: 7594754 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.4208. Min Act: -0.1700
Data Index: 6855198 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.4520. Min Act: -0.1700
Data Index: 3501695 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.3895. Min Act: -0.1700
Data Index: 1071232 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.3895. Min Act: -0.1700
Data Index: 6665922 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.3583. Min Act: -0.1700
Data Index: 8828504 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.3270. Min Act: -0.1700
Data Index: 1684731 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.3270. Min Act: -0.1700
Data Index: 7094503 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.2958. Min Act: -0.1700
Data Index: 6587787 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.3270. Min Act: -0.1700
Data Index: 5572177 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.2645. Min Act: -0.1700
Data Index: 3950881 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.2958. Min Act: -0.1700
Data Index: 3528875 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.2958. Min Act: -0.1700
Data Index: 4900059 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19