Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3053 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.4934. Min Act: -0.1700
Data Index: 4283317 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.4621. Min Act: -0.1700
Data Index: 1345152 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.4309. Min Act: -0.1700
Data Index: 4510466 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.4621. Min Act: -0.1700
Data Index: 3997449 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.3996. Min Act: -0.1700
Data Index: 1529676 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.3371. Min Act: -0.1700
Data Index: 4549281 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.2434. Min Act: -0.1700
Data Index: 1776111 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.1809. Min Act: -0.1700
Data Index: 3322146 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.2121. Min Act: -0.1700
Data Index: 6142884 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.1809. Min Act: -0.1700
Data Index: 1194838 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.1809. Min Act: -0.1700
Data Index: 3006797 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.1496. Min Act: -0.1700
Data Index: 4297512 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.1496. Min Act: -0.1700
Data Index: 1468352 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.1496. Min Act: -0.1700
Data Index: 5595864 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.1184. Min Act: -0.1700
Data Index: 3366885 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.1184. Min Act: -0.1700
Data Index: 7174855 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.1184. Min Act: -0.1700
Data Index: 7144027 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.1184. Min Act: -0.1700
Data Index: 5319757 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.1184. Min Act: -0.1700
Data Index: 1719411 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4934. Min Range: -4.4934
Max Act: 4.0871. Min Act: -0.1700
Data Index: 2570603 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19