Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3060 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.5971. Min Act: -0.1700
Data Index: 1358421 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.5658. Min Act: -0.1700
Data Index: 3608003 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.5346. Min Act: -0.1700
Data Index: 3124953 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.5346. Min Act: -0.1700
Data Index: 7994497 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.5033. Min Act: -0.1700
Data Index: 6887835 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.4096. Min Act: -0.1700
Data Index: 1314304 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.4096. Min Act: -0.1700
Data Index: 4093306 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.3158. Min Act: -0.1700
Data Index: 6374076 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.2846. Min Act: -0.1700
Data Index: 786219 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.3158. Min Act: -0.1700
Data Index: 7320151 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.2846. Min Act: -0.1700
Data Index: 6853264 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.2221. Min Act: -0.1700
Data Index: 4892486 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.2221. Min Act: -0.1700
Data Index: 7184472 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.2221. Min Act: -0.1700
Data Index: 7232540 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.1908. Min Act: -0.1700
Data Index: 153888 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.2221. Min Act: -0.1700
Data Index: 7901821 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.1596. Min Act: -0.1700
Data Index: 2405566 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.1283. Min Act: -0.1700
Data Index: 8150099 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.1283. Min Act: -0.1700
Data Index: 5058296 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5971. Min Range: -5.5971
Max Act: 5.1283. Min Act: -0.1700
Data Index: 91192 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19