Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5161 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3369. Min Range: -6.3369
Max Act: 6.3369. Min Act: -0.1700
Data Index: 5346889 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3369. Min Range: -6.3369
Max Act: 6.1806. Min Act: -0.1700
Data Index: 5245188 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.9931. Min Act: -0.1700
Data Index: 3070578 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.8994. Min Act: -0.1700
Data Index: 5974774 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.8681. Min Act: -0.1700
Data Index: 31919 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.8369. Min Act: -0.1700
Data Index: 101843 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.8369. Min Act: -0.1700
Data Index: 3393778 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.7744. Min Act: -0.1700
Data Index: 6304196 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.7431. Min Act: -0.1700
Data Index: 5085435 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.7119. Min Act: -0.1700
Data Index: 1721852 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.7431. Min Act: -0.1700
Data Index: 454069 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.7119. Min Act: -0.1700
Data Index: 1731926 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.7119. Min Act: -0.1700
Data Index: 4214829 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.6806. Min Act: -0.1700
Data Index: 124065 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.6494. Min Act: -0.1700
Data Index: 4409945 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.6494. Min Act: -0.1700
Data Index: 6177007 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.6494. Min Act: -0.1700
Data Index: 1903636 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.6494. Min Act: -0.1700
Data Index: 4479392 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.6494. Min Act: -0.1700
Data Index: 1239958 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3369. Min Range: -6.3369
Max Act: 5.6181. Min Act: -0.1700
Data Index: 470466 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19