Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3372 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.5142. Min Act: -0.1700
Data Index: 809410 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.4830. Min Act: -0.1700
Data Index: 4951541 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.3892. Min Act: -0.1700
Data Index: 1914774 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.2642. Min Act: -0.1700
Data Index: 66043 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.2642. Min Act: -0.1700
Data Index: 750656 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.2642. Min Act: -0.1700
Data Index: 2509448 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.2642. Min Act: -0.1700
Data Index: 494556 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.2330. Min Act: -0.1700
Data Index: 8216110 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.2330. Min Act: -0.1700
Data Index: 2376945 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.2330. Min Act: -0.1700
Data Index: 6701620 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.2642. Min Act: -0.1700
Data Index: 8739020 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.2017. Min Act: -0.1700
Data Index: 8097633 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.2017. Min Act: -0.1700
Data Index: 7601113 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.1705. Min Act: -0.1700
Data Index: 4520559 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.2017. Min Act: -0.1700
Data Index: 1186971 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.1705. Min Act: -0.1700
Data Index: 3334017 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.1705. Min Act: -0.1700
Data Index: 7155960 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.1705. Min Act: -0.1700
Data Index: 4225832 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.1705. Min Act: -0.1700
Data Index: 5550502 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5142. Min Range: -4.5142
Max Act: 4.1392. Min Act: -0.1700
Data Index: 1711973 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19