Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3045 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0145. Min Range: -5.0145
Max Act: 5.0145. Min Act: -0.1700
Data Index: 918413 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0145. Min Range: -5.0145
Max Act: 5.0145. Min Act: -0.1700
Data Index: 3444186 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0145. Min Range: -5.0145
Max Act: 5.0145. Min Act: -0.1700
Data Index: 2547771 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.9832. Min Act: -0.1700
Data Index: 4271899 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.9832. Min Act: -0.1700
Data Index: 530646 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.9832. Min Act: -0.1700
Data Index: 2219779 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.9520. Min Act: -0.1700
Data Index: 2989779 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.9520. Min Act: -0.1700
Data Index: 7171364 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.9520. Min Act: -0.1700
Data Index: 300431 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.9207. Min Act: -0.1700
Data Index: 4564158 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.9207. Min Act: -0.1700
Data Index: 1749639 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.9207. Min Act: -0.1700
Data Index: 1490057 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.9207. Min Act: -0.1700
Data Index: 4925990 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.8895. Min Act: -0.1700
Data Index: 5308384 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.8895. Min Act: -0.1700
Data Index: 2897696 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.8895. Min Act: -0.1700
Data Index: 3709322 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.8895. Min Act: -0.1700
Data Index: 5382955 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.8895. Min Act: -0.1700
Data Index: 3033848 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.8582. Min Act: -0.1700
Data Index: 2961097 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0145. Min Range: -5.0145
Max Act: 4.8582. Min Act: -0.1700
Data Index: 864969 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19